Add YAML frontmatter to all skills for automatic discovery

Skills require YAML frontmatter with name and description fields
for Claude Code to automatically discover and load them. Added
frontmatter to all five skill files:
- gitea: CLI for issues, PRs, and repository management
- code-review: Guidelines for reviewing code changes
- issue-writing: How to write clear, actionable issues
- backlog-grooming: Review and improve existing issues
- roadmap-planning: Plan features and create issues

Closes #12

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.gitignore

@@ -16,11 +16,3 @@
 secrets/
 *.pem
 *.key
-
-# opencode
-.opencode/opencode.json
-.opencode/package-lock.json
-
-node_modules
-bun.lock
-package-lock.json

.opencode/tools/git-worktree-create.ts

@@ -1,13 +0,0 @@
-import { tool } from "@opencode-ai/plugin"
-import { $ } from "bun"
-
-export default tool({
-  description: "Create a git worktree for a branch or PR",
-  args: {
-    branch: tool.schema.string().describe("Branch name or PR number"),
-  },
-  async execute(args) {
-    const result = await $`git worktree add ../worktrees/${args.branch}`.text()
-    return result.trim()
-  },
-})

.opencode/tools/tea-actions-runs-list.ts

@@ -1,23 +0,0 @@
-import { tool } from "@opencode-ai/plugin"
-import { $ } from "bun"
-
-export default tool({
-  description: "List workflow runs for Gitea actions with optional filters",
-  args: {
-    status: tool.schema.string().optional().describe("Filter by status (success, failure, pending, queued, in_progress, skipped, canceled)"),
-    branch: tool.schema.string().optional().describe("Filter by branch name"),
-    event: tool.schema.string().optional().describe("Filter by event type (push, pull_request, etc.)"),
-    limit: tool.schema.number().optional().describe("Number of results to return (default: 30)"),
-    since: tool.schema.string().optional().describe("Show runs started after this time (e.g., '24h', '7d')"),
-  },
-  async execute(args) {
-    let cmd = [`tea`, `actions`, `runs`, `list`, `-o`, `json`]
-    if (args.status) cmd = [...cmd, `--status`, args.status]
-    if (args.branch) cmd = [...cmd, `--branch`, args.branch]
-    if (args.event) cmd = [...cmd, `--event`, args.event]
-    if (args.limit) cmd = [...cmd, `--limit`, String(args.limit)]
-    if (args.since) cmd = [...cmd, `--since`, args.since]
-    const result = await $`${cmd}`.text()
-    return result.trim()
-  },
-})

.opencode/tools/tea-actions-runs-logs.ts

@@ -1,17 +0,0 @@
-import { tool } from "@opencode-ai/plugin"
-import { $ } from "bun"
-
-export default tool({
-  description: "Get logs for a specific Gitea actions workflow run to diagnose failures",
-  args: {
-    runId: tool.schema.number().describe("Workflow run ID to get logs for"),
-    job: tool.schema.string().optional().describe("Specific job ID to view (if omitted, shows all jobs)"),
-  },
-  async execute(args) {
-    let cmd = [`tea`, `actions`, `runs`, `logs`]
-    if (args.job) cmd = [...cmd, `--job`, args.job]
-    cmd = [...cmd, String(args.runId), `-o`, `simple`]
-    const result = await $`${cmd}`.text()
-    return result.trim()
-  },
-})

.opencode/tools/tea-comment.ts

@@ -1,14 +0,0 @@
-import { tool } from "@opencode-ai/plugin"
-import { $ } from "bun"
-
-export default tool({
-  description: "Add a comment to a specific issue using tea CLI",
-  args: {
-    issueNumber: tool.schema.number().describe("Issue number/index"),
-    body: tool.schema.string().describe("Comment body"),
-  },
-  async execute(args) {
-    const result = await $`tea comment ${args.issueNumber} ${args.body}`.text()
-    return result.trim()
-  },
-})

.opencode/tools/tea-issue-create.ts

@@ -1,14 +0,0 @@
-import { tool } from "@opencode-ai/plugin"
-import { $ } from "bun"
-
-export default tool({
-  description: "Create a new issue in the GitHub repository using tea CLI",
-  args: {
-    title: tool.schema.string().describe("Issue title"),
-    description: tool.schema.string().optional().describe("Issue description (supports markdown)"),
-  },
-  async execute(args) {
-    const result = await $`tea issues create -t ${args.title} -d ${args.description}`.text()
-    return result.trim()
-  },
-})

.opencode/tools/tea-issue-get.ts

@@ -1,13 +0,0 @@
-import { tool } from "@opencode-ai/plugin"
-import { $ } from "bun"
-
-export default tool({
-  description: "Get a specific issue with all details and comments using tea CLI",
-  args: {
-    issueNumber: tool.schema.number().describe("Issue number/index"),
-  },
-  async execute(args) {
-    const result = await $`tea issues ${args.issueNumber} --comments --output json`.text()
-    return result.trim()
-  },
-})

.opencode/tools/tea-issues.ts

@@ -1,11 +0,0 @@
-import { tool } from "@opencode-ai/plugin"
-import { $ } from "bun"
-
-export default tool({
-  description: "List all issues in the project using tea CLI",
-  args: {},
-  async execute(args, context) {
-    const result = await $`tea issues list`.text()
-    return result.trim()
-  },
-})

.opencode/tools/tea-pr-create.ts

@@ -1,24 +0,0 @@
-import { tool } from "@opencode-ai/plugin"
-import { $ } from "bun"
-
-export default tool({
-  description: "Create a pull request in the repository using tea CLI",
-  args: {
-    title: tool.schema.string().describe("PR title"),
-    head: tool.schema.string().optional().describe("Branch name of the PR source (defaults to current branch)"),
-    base: tool.schema.string().optional().describe("Branch name of the PR target (defaults to repository default branch)"),
-    description: tool.schema.string().optional().describe("PR description (supports markdown)"),
-    assignees: tool.schema.string().optional().describe("Comma-separated list of usernames to assign"),
-    labels: tool.schema.string().optional().describe("Comma-separated list of labels to assign"),
-  },
-  async execute(args) {
-    let cmd = [`tea`, `pulls`, `create`, `-t`, args.title]
-    if (args.head) cmd = [...cmd, `--head`, args.head]
-    if (args.base) cmd = [...cmd, `-b`, args.base]
-    if (args.description) cmd = [...cmd, `-d`, args.description]
-    if (args.assignees) cmd = [...cmd, `-a`, args.assignees]
-    if (args.labels) cmd = [...cmd, `-L`, args.labels]
-    const result = await $`${cmd}`.text()
-    return result.trim()
-  },
-})

.opencode/tools/tea-pr-get.ts

@@ -1,13 +0,0 @@
-import { tool } from "@opencode-ai/plugin"
-import { $ } from "bun"
-
-export default tool({
-  description: "Get a specific pull request with all details and comments using tea CLI",
-  args: {
-    pullNumber: tool.schema.number().describe("Pull request number/index"),
-  },
-  async execute(args) {
-    const result = await $`tea pulls ${args.pullNumber} --comments --output json`.text()
-    return result.trim()
-  },
-})

.opencode/tools/tea-pulls.ts

@@ -1,14 +0,0 @@
-import { tool } from "@opencode-ai/plugin"
-import { $ } from "bun"
-
-export default tool({
-  description: "List pull requests in the repository using tea CLI",
-  args: {
-    state: tool.schema.string().optional().describe("Filter by state (all|open|closed)"),
-  },
-  async execute(args) {
-    const state = args.state || "open"
-    const result = await $`tea pulls --state ${state} --output json`.text()
-    return result.trim()
-  },
-})

ARCHITECTURE.md

@@ -0,0 +1,426 @@
+# Architecture
+
+This document explains how the three component types—Commands, Skills, and Agents—work together to create a composable AI workflow system.
+
+## Overview
+
+The architecture follows a layered composition model where each component type serves a distinct purpose:
+
+```
+┌─────────────────────────────────────────────────────────────────┐
+│                         USER                                    │
+│                           │                                     │
+│                           ▼                                     │
+│  ┌─────────────────────────────────────────────────────────┐   │
+│  │                      COMMANDS                            │   │
+│  │           User-facing entry points                       │   │
+│  │   /work-issue  /dashboard  /plan-issues  /groom         │   │
+│  └─────────────────────────────────────────────────────────┘   │
+│                           │                                     │
+│              ┌────────────┼────────────┐                       │
+│              ▼            ▼            ▼                       │
+│  ┌─────────────────┐ ┌─────────────────────────────────────┐   │
+│  │     AGENTS      │ │              SKILLS                  │   │
+│  │  Specialized    │ │         Knowledge modules            │   │
+│  │   subagents     │ │                                      │   │
+│  │                 │ │  issue-writing    gitea            │   │
+│  │ product-manager │ │  backlog-grooming roadmap-planning   │   │
+│  └─────────────────┘ └─────────────────────────────────────┘   │
+│              │                    ▲                            │
+│              └────────────────────┘                            │
+│                   Agents use skills                            │
+└─────────────────────────────────────────────────────────────────┘
+```
+
+## Components
+
+### Commands
+
+**Location:** `commands/*.md`
+
+Commands are user-facing entry points that trigger workflows. They define *what* to do, not *how* to do it.
+
+#### Structure
+
+Each command file contains:
+- **Frontmatter**: Metadata including description and argument hints
+- **Instructions**: Step-by-step workflow for Claude to follow
+- **Tool references**: Which CLI tools or skills to invoke
+
+```yaml
+---
+description: Work on a Gitea issue
+argument-hint: <issue-number>
+---
+
+# Work on Issue #$1
+
+1. **View the issue**: `tea issues $1`
+2. **Create a branch**: `git checkout -b issue-$1-<title>`
+...
+```
+
+#### Characteristics
+
+- **Invoked explicitly** by users via `/command-name`
+- **Self-contained workflows** with clear start and end
+- **May use skills** for domain knowledge
+- **May spawn agents** for complex subtasks
+- **Request approval** before significant actions
+
+#### When to Create a Command
+
+Create a command when you have:
+- A repeatable workflow with clear steps
+- User-initiated action (not automatic)
+- Need for consistent behavior across sessions
+
+#### Current Commands
+
+| Command | Purpose | Skills Used |
+|---------|---------|-------------|
+| `/work-issue` | Implement an issue end-to-end | gitea |
+| `/dashboard` | View open issues and PRs | gitea |
+| `/review-pr` | Review and act on a PR | gitea |
+| `/create-issue` | Create single or batch issues | gitea, issue-writing |
+| `/groom` | Improve issue quality | backlog-grooming, issue-writing |
+| `/roadmap` | View issues organized by status | gitea, roadmap-planning |
+| `/plan-issues` | Break down features into issues | roadmap-planning, issue-writing, gitea |
+
+---
+
+### Skills
+
+**Location:** `skills/<skill-name>/SKILL.md`
+
+Skills are knowledge modules—focused documents that teach Claude how to do something well. They encode domain expertise and best practices.
+
+#### Structure
+
+Each skill file contains:
+- **Conceptual knowledge**: What Claude needs to understand
+- **Patterns and templates**: Reusable structures
+- **Guidelines and checklists**: Quality standards
+- **Examples**: Concrete illustrations
+
+```markdown
+# Issue Writing
+
+How to write clear, actionable issues.
+
+## Issue Structure
+### Title
+- Start with action verb: "Add", "Fix", "Update"
+- Be specific: "Add user authentication" not "Auth stuff"
+...
+```
+
+#### Characteristics
+
+- **Passive knowledge** that doesn't act on its own
+- **Focused scope**: one domain, one concern
+- **Composable**: multiple skills can be combined
+- **Referenced** by commands and agents
+- **No side effects**: information only
+
+#### When to Create a Skill
+
+Create a skill when you find yourself:
+- Explaining the same concepts repeatedly
+- Wanting consistent quality in a specific area
+- Building up domain expertise that should persist
+
+#### Current Skills
+
+| Skill | Purpose |
+|-------|---------|
+| `gitea` | How to use the Gitea CLI for issues and PRs |
+| `issue-writing` | How to structure clear, actionable issues |
+| `backlog-grooming` | How to review and improve existing issues |
+| `roadmap-planning` | How to plan features and create issue breakdowns |
+| `code-review` | How to review code for quality, bugs, security, and style |
+
+---
+
+### Agents
+
+**Location:** `agents/<agent-name>/AGENT.md`
+
+Agents are specialized subagents that combine multiple skills into focused personas. They can work autonomously on complex tasks with isolated context.
+
+#### Structure
+
+Each agent file uses YAML frontmatter followed by a system prompt:
+
+```markdown
+---
+name: agent-name
+description: When this agent should be invoked (used for automatic delegation)
+model: inherit
+skills: skill1, skill2, skill3
+---
+
+You are a [role] specializing in [domain].
+
+## Capabilities
+
+You can:
+- Do thing one
+- Do thing two
+
+## Behavior
+
+- Guideline one
+- Guideline two
+```
+
+#### Frontmatter Fields
+
+| Field | Required | Description |
+|-------|----------|-------------|
+| `name` | Yes | Unique identifier (lowercase, hyphens) |
+| `description` | Yes | When to use this agent (enables auto-delegation) |
+| `model` | No | `sonnet`, `opus`, `haiku`, or `inherit` |
+| `skills` | No | Comma-separated skill names to auto-load |
+| `tools` | No | Limit available tools (inherits all if omitted) |
+
+#### Characteristics
+
+- **Isolated context**: Each agent maintains separate conversation state
+- **Skill composition**: Combines multiple skills for complex tasks
+- **Autonomous operation**: Can work with minimal intervention
+- **Spawned by commands**: Commands decide when to use agents
+- **Returns results**: Reports back to the main conversation
+
+#### When to Create an Agent
+
+Create an agent when you need:
+- To combine multiple skills for a role
+- Parallel processing of independent tasks
+- Isolated context to prevent pollution
+- Autonomous handling of complex workflows
+
+#### Current Agents
+
+| Agent | Skills | Use Case |
+|-------|--------|----------|
+| `product-manager` | gitea, issue-writing, backlog-grooming, roadmap-planning | Batch issue operations, backlog reviews, feature planning |
+| `code-reviewer` | gitea, code-review | Automated PR review, quality checks |
+
+---
+
+## Data and Control Flow
+
+### Invocation Flow
+
+```
+User invokes command
+        │
+        ▼
+┌───────────────────┐
+│ Command executes  │
+│ workflow steps    │
+└───────────────────┘
+        │
+        ├─── Direct action (git, tea CLI)
+        │
+        ├─── Reference skill for knowledge
+        │           │
+        │           ▼
+        │    ┌─────────────────┐
+        │    │ Skill provides  │
+        │    │ patterns and    │
+        │    │ guidelines      │
+        │    └─────────────────┘
+        │
+        └─── Spawn agent for complex subtask
+                    │
+                    ▼
+             ┌─────────────────┐
+             │ Agent works     │
+             │ autonomously    │
+             │ with its skills │
+             └─────────────────┘
+                    │
+                    ▼
+             Results return to command
+```
+
+### Example: `/plan-issues add dark mode`
+
+1. **Command invoked**: User runs `/plan-issues add dark mode`
+
+2. **Skills consulted**:
+   - `roadmap-planning`: How to break down features
+   - `issue-writing`: How to structure each issue
+   - `gitea`: How to create issues via CLI
+
+3. **Workflow executed**:
+   - Analyze what "dark mode" involves
+   - Break down into discrete issues
+   - Present plan for approval
+   - Create issues in dependency order
+
+4. **Output**: Issues created with proper structure and references
+
+### Example: `/groom` (batch mode)
+
+1. **Command invoked**: User runs `/groom` with no argument
+
+2. **Skills consulted**:
+   - `backlog-grooming`: Checklist and evaluation criteria
+   - `issue-writing`: Standards for improvements
+
+3. **Potential agent spawn**: For many issues, could spawn `product-manager` agent
+
+4. **Agent workflow**:
+   - Fetches all open issues
+   - Evaluates each against grooming checklist
+   - Categorizes as ready/needs-work/stale
+   - Proposes improvements
+
+5. **Output**: Summary table with suggestions, optional issue updates
+
+---
+
+## Component Relationships
+
+### How Commands Use Skills
+
+Commands reference skills by name in their instructions:
+
+```markdown
+# Groom Issues
+
+Use the backlog-grooming and issue-writing skills.
+```
+
+Claude reads the referenced skill files to gain the necessary knowledge before executing the command workflow.
+
+### How Agents Use Skills
+
+Agents declare their skills in the YAML frontmatter:
+
+```yaml
+---
+name: product-manager
+skills: gitea, issue-writing, backlog-grooming
+---
+```
+
+When spawned, the agent has access to all listed skills as part of its context.
+
+### How Commands Spawn Agents
+
+Commands can delegate to agents for complex subtasks:
+
+```markdown
+For comprehensive backlog review, spawn the product-manager agent.
+```
+
+The agent works autonomously and returns results to the command.
+
+---
+
+## Design Principles
+
+### Separation of Concerns
+
+- **Commands**: Define workflows (what to do)
+- **Skills**: Encode knowledge (how to do it well)
+- **Agents**: Execute complex tasks (who does it)
+
+### Composability
+
+Small, focused components combine to handle complex scenarios:
+
+```
+/plan-issues = roadmap-planning + issue-writing + gitea
+product-manager = all four skills combined
+```
+
+### Single Responsibility
+
+Each component has one clear purpose:
+- One command = one workflow
+- One skill = one domain
+- One agent = one role
+
+### Progressive Enhancement
+
+Start simple, add complexity as needed:
+1. Use skills directly for simple tasks
+2. Create commands for repeatable workflows
+3. Add agents for complex parallel work
+
+---
+
+## File Structure
+
+```
+ai/
+├── commands/                    # User-invoked workflows
+│   ├── work-issue.md
+│   ├── dashboard.md
+│   ├── review-pr.md
+│   ├── create-issue.md
+│   ├── groom.md
+│   ├── roadmap.md
+│   └── plan-issues.md
+├── skills/                      # Knowledge modules
+│   ├── gitea/
+│   │   └── SKILL.md
+│   ├── issue-writing/
+│   │   └── SKILL.md
+│   ├── backlog-grooming/
+│   │   └── SKILL.md
+│   ├── roadmap-planning/
+│   │   └── SKILL.md
+│   └── code-review/
+│       └── SKILL.md
+├── agents/                      # Specialized subagents
+│   ├── product-manager/
+│   │   └── AGENT.md
+│   └── code-reviewer/
+│       └── AGENT.md
+├── scripts/                     # Hook scripts
+│   └── pre-commit-checks.sh
+├── settings.json                # Claude Code configuration
+├── CLAUDE.md                    # Project instructions
+├── VISION.md                    # Why this project exists
+└── ARCHITECTURE.md              # This document
+```
+
+---
+
+## Adding New Components
+
+### Adding a Command
+
+1. Create `commands/<name>.md`
+2. Add frontmatter with description and argument hints
+3. Define the workflow steps
+4. Reference any needed skills
+5. Test the workflow
+
+### Adding a Skill
+
+1. Create `skills/<name>/SKILL.md`
+2. Document the domain knowledge
+3. Include patterns, templates, and examples
+4. Reference from commands or agents as needed
+
+### Adding an Agent
+
+1. Create `agents/<name>/AGENT.md`
+2. Add YAML frontmatter with `name`, `description`, and `skills`
+3. Write system prompt defining capabilities and behavior
+4. Update commands to use the agent where appropriate
+
+---
+
+## See Also
+
+- [VISION.md](VISION.md): The philosophy and goals behind this project
+- [CLAUDE.md](CLAUDE.md): Setup and configuration instructions
+- [README.md](README.md): Project overview and quick start

CLAUDE.md

@@ -0,0 +1,52 @@
+# Claude Code AI Workflow
+
+This repository contains configurations, prompts, and tools to improve the Claude Code AI workflow.
+
+## Setup
+
+```bash
+# Clone and install symlinks
+git clone ssh://git@code.flowmade.one/flowmade-one/ai.git
+cd ai
+make install
+```
+
+## Project Structure
+
+```
+ai/
+├── commands/       # Slash commands (/work-issue, /dashboard)
+├── skills/         # Auto-triggered capabilities
+├── agents/         # Subagents with isolated context
+├── scripts/        # Hook scripts (pre-commit, token loading)
+├── settings.json   # Claude Code settings
+└── Makefile        # Install/uninstall symlinks
+```
+
+All files symlink to `~/.claude/` via `make install`.
+
+## Gitea Integration
+
+Uses `tea` CLI for issue/PR management:
+
+```bash
+# Setup (one-time)
+brew install tea
+tea logins add --name flowmade --url https://git.flowmade.one --token <your-token>
+
+# Create token at: https://git.flowmade.one/user/settings/applications
+```
+
+### Available Commands
+
+| Command | Description |
+|---------|-------------|
+| `/work-issue <n>` | Fetch issue, create branch, implement, create PR |
+| `/dashboard` | Show open issues and PRs |
+| `/review-pr <n>` | Review PR with diff and comments |
+| `/create-issue` | Create single or batch issues |
+| `/retro` | Capture learnings from completed work, create improvement issues |
+
+## Usage
+
+This project is meant to be used alongside Claude Code to enhance productivity and maintain consistent workflows.

Makefile

@@ -1,71 +1,54 @@
-.PHONY: install uninstall status start-llm stop-llm restart-llm
+.PHONY: install uninstall status
 
-OPENCODE_DIR := $(HOME)/.config/opencode
+CLAUDE_DIR := $(HOME)/.claude
 REPO_DIR := $(shell pwd)
 
 # Items to symlink
-ITEMS := skills tools agents
+ITEMS := commands scripts skills agents settings.json
-
-# LLM services to manage
-LLM_SERVICES := odin
-
-PLIST_PATH := ~/Library/LaunchAgents
 
 install:
-	@echo "Installing OpenCode config symlinks..."
+	@echo "Installing Claude Code config symlinks..."
-	@mkdir -p $(OPENCODE_DIR)
+	@mkdir -p $(CLAUDE_DIR)
 	@for item in $(ITEMS); do \
-		if [ -e "$(REPO_DIR)/.opencode/$$item" ]; then \
+		if [ -e "$(REPO_DIR)/$$item" ]; then \
-			if [ -L "$(OPENCODE_DIR)/$$item" ]; then \
+			if [ -L "$(CLAUDE_DIR)/$$item" ]; then \
 				echo "  $$item: already symlinked"; \
+			elif [ -e "$(CLAUDE_DIR)/$$item" ]; then \
+				echo "  $$item: backing up existing to $$item.bak"; \
+				mv "$(CLAUDE_DIR)/$$item" "$(CLAUDE_DIR)/$$item.bak"; \
+				ln -s "$(REPO_DIR)/$$item" "$(CLAUDE_DIR)/$$item"; \
+				echo "  $$item: symlinked"; \
 			else \
-				ln -s "$(REPO_DIR)/.opencode/$$item" "$(OPENCODE_DIR)/$$item"; \
+				ln -s "$(REPO_DIR)/$$item" "$(CLAUDE_DIR)/$$item"; \
 				echo "  $$item: symlinked"; \
 			fi \
-		else \
-			echo "  $$item: skipped (not found)"; \
 		fi \
 	done
-	@echo "Done!"
+	@echo "Done! Restart Claude Code to apply changes."
 
 uninstall:
-	@echo "Removing OpenCode config symlinks..."
+	@echo "Removing Claude Code config symlinks..."
 	@for item in $(ITEMS); do \
-		if [ -L "$(OPENCODE_DIR)/$$item" ]; then \
+		if [ -L "$(CLAUDE_DIR)/$$item" ]; then \
-			rm "$(OPENCODE_DIR)/$$item"; \
+			rm "$(CLAUDE_DIR)/$$item"; \
 			echo "  $$item: removed symlink"; \
+			if [ -e "$(CLAUDE_DIR)/$$item.bak" ]; then \
+				mv "$(CLAUDE_DIR)/$$item.bak" "$(CLAUDE_DIR)/$$item"; \
+				echo "  $$item: restored backup"; \
+			fi \
 		fi \
 	done
 	@echo "Done!"
 
 status:
-	@echo "OpenCode config status:"
+	@echo "Claude Code config status:"
 	@for item in $(ITEMS); do \
-		if [ -L "$(OPENCODE_DIR)/$$item" ]; then \
+		if [ -L "$(CLAUDE_DIR)/$$item" ]; then \
-			target=$$(readlink "$(OPENCODE_DIR)/$$item"); \
+			target=$$(readlink "$(CLAUDE_DIR)/$$item"); \
 			echo "  $$item: symlink -> $$target"; \
-		elif [ -e "$(OPENCODE_DIR)/$$item" ]; then \
+		elif [ -e "$(CLAUDE_DIR)/$$item" ]; then \
 			echo "  $$item: exists (not symlinked)"; \
 		else \
 			echo "  $$item: not found"; \
 		fi \
 	done
-
-stop-llm-%:
-	@echo "Stopping com.vllm-mlx-$*..."
-	@launchctl bootout gui/$$(id -u) $(PLIST_PATH)/com.vllm-mlx.$*.plist 2>/dev/null || true
-
-stop-llm: $(patsubst %,stop-llm-%,$(LLM_SERVICES))
-
-start-llm-%:
-	@echo "Starting com.vllm-mlx-$*..."
-	@launchctl bootstrap gui/$$(id -u) $(PLIST_PATH)/com.vllm-mlx.$*.plist
-
-start-llm: $(patsubst %,start-llm-%,$(LLM_SERVICES))
-
-restart-llm-%:
-	@echo "Restarting com.vllm-mlx-$*..."
-	@launchctl bootout gui/$$(id -u) $(PLIST_PATH)/com.vllm-mlx.$*.plist || true
-	@launchctl bootstrap gui/$$(id -u) $(PLIST_PATH)/com.vllm-mlx.$*.plist
-
-restart-llm: $(patsubst %,restart-llm-%,$(LLM_SERVICES))

README.md

@@ -1,154 +1,178 @@
-# Architecture
+# Claude Code AI Workflow
 
-The organizational source of truth for how we build software with OpenCode.
+A composable toolkit for enhancing [Claude Code](https://claude.ai/claude-code) with structured workflows, issue management, and AI-assisted development practices.
 
-This repository contains the structure for our OpenCode configuration: skills, tools, and agents that make AI-assisted development predictable and effective.
+## Why This Project?
+
+Claude Code is powerful, but its effectiveness depends on how you use it. This project provides:
+
+- **Structured workflows** for common development tasks (issue tracking, PR reviews, planning)
+- **Composable components** that build on each other (skills, agents, commands)
+- **Forgejo integration** for seamless issue and PR management
+- **Consistent patterns** that make AI assistance more predictable and effective
 
 ## Core Concepts
 
-OpenCode uses three component types:
+The project is built around three composable component types:
 
-| Component | Location | Purpose | Example |
+```
-|-----------|----------|---------|---------|
+┌─────────────────────────────────────────────────────────┐
-| **Skills** | `.opencode/skills/` | Reference knowledge | `issue-writing` knows how to structure good issues |
+│                      COMMANDS                           │
-| **Tools** | `.opencode/tools/` | Custom functions | `spawn_issues` implements multiple issues in parallel |
+│         User-facing entry points (/work-issue)          │
-| **Agents** | `.opencode/agents/` | Specialized subagents | `code-reviewer` handles PR reviews |
+│                         │                               │
+│                         ▼                               │
+│  ┌─────────────────────────────────────────────────┐   │
+│  │                    AGENTS                        │   │
+│  │    Subprocesses with isolated context            │   │
+│  │    (parallel processing, complex workflows)      │   │
+│  │                      │                           │   │
+│  │                      ▼                           │   │
+│  │  ┌───────────────────────────────────────────┐  │   │
+│  │  │                 SKILLS                     │  │   │
+│  │  │   Reusable knowledge modules               │  │   │
+│  │  │   (gitea, issue-writing, planning)       │  │   │
+│  │  └───────────────────────────────────────────┘  │   │
+│  └─────────────────────────────────────────────────┘   │
+└─────────────────────────────────────────────────────────┘
+```
+
+| Component | Purpose | Example |
+|-----------|---------|---------|
+| **Commands** | Entry points users invoke directly | `/work-issue 42` starts implementation workflow |
+| **Skills** | Domain knowledge modules | `issue-writing` knows how to structure good issues |
+| **Agents** | Autonomous subprocesses | `product-manager` combines skills for complex planning |
 
 ## Quick Start
 
+### Prerequisites
+
+- [Claude Code CLI](https://claude.ai/claude-code) installed
+- [Forgejo CLI](https://code.gitea.org/gitea/gitea-cli) (`tea`) for issue/PR management
+
 ### Installation
 
 ```bash
 # Clone the repository
-git clone ssh://git@code.flowmade.one/flowmade-one/architecture.git
+git clone ssh://git@code.flowmade.one/flowmade-one/ai.git
-cd architecture
+cd ai
 
-# Install symlinks to ~/.config/opencode/
+# Install symlinks to ~/.claude/
 make install
 ```
 
-This creates symlinks at:
+### Forgejo Setup
-- `~/.config/opencode/skills/` → `.opencode/skills/`
-- `~/.config/opencode/tools/` → `.opencode/tools/`
-- `~/.config/opencode/agents/` → `.opencode/agents/`
 
-### Uninstallation
+```bash
+# Install gitea-cli
+brew install gitea-cli
+
+# Authenticate (one-time)
+echo "YOUR_TOKEN" | tea -H code.flowmade.one auth add-key username
+
+# Required token scopes: read:user, read:repository, write:issue, write:repository
+```
+
+## Available Commands
+
+| Command | Description |
+|---------|-------------|
+| `/dashboard` | Show open issues and PRs for the current repo |
+| `/work-issue <n>` | Fetch issue, create branch, implement, and create PR |
+| `/review-pr <n>` | Review a PR with diff analysis and feedback |
+| `/create-issue` | Create single or batch issues interactively |
+| `/plan-issues <desc>` | Break down a feature into discrete issues |
+| `/groom [n]` | Improve issue quality (single or batch) |
+| `/roadmap` | Visualize issues by status and dependencies |
+
+## Project Structure
+
+```
+ai/
+├── commands/           # Slash commands invoked by users
+│   ├── work-issue.md
+│   ├── dashboard.md
+│   ├── review-pr.md
+│   ├── create-issue.md
+│   ├── plan-issues.md
+│   ├── groom.md
+│   └── roadmap.md
+├── skills/             # Reusable knowledge modules
+│   ├── gitea/        # Forgejo CLI integration
+│   ├── issue-writing/  # Issue structure best practices
+│   ├── backlog-grooming/  # Backlog maintenance
+│   ├── roadmap-planning/  # Feature breakdown
+│   └── code-review/    # Code review best practices
+├── agents/             # Specialized subagents
+│   ├── product-manager/  # Combines skills for PM tasks
+│   └── code-reviewer/  # Automated PR code review
+├── scripts/            # Git hooks and utilities
+│   └── pre-commit-checks.sh
+├── settings.json       # Claude Code configuration
+├── Makefile            # Symlink management
+└── CLAUDE.md           # Instructions for Claude Code
+```
+
+## Example Workflows
+
+### Working on an Issue
+
+```
+> /work-issue 42
+
+Fetching issue #42: "Add user authentication"
+Creating branch: feature/42-add-user-authentication
+Planning implementation...
+[Claude implements the feature]
+Creating PR with reference to issue...
+```
+
+### Planning a Feature
+
+```
+> /plan-issues Add dark mode support
+
+Proposed Issues:
+1. Create theme context and provider
+2. Add theme toggle component
+3. Update components to use theme variables
+4. Add system preference detection
+
+Create these issues? [y/n]
+```
+
+### Daily Standup
+
+```
+> /dashboard
+
+Open Issues (3):
+| #  | Title                    | Labels      |
+|----|--------------------------|-------------|
+| 42 | Add user authentication  | feature     |
+| 38 | Fix login redirect       | bug         |
+| 35 | Update dependencies      | maintenance |
+
+Open PRs (1):
+| #  | Title                    | Status      |
+|----|--------------------------|-------------|
+| 41 | Add password reset flow  | review      |
+```
+
+## Configuration
+
+The `settings.json` configures Claude Code behavior:
+
+- **Model selection**: Uses Opus for complex tasks
+- **Status line**: Shows git branch and status
+- **Hooks**: Pre-commit validation for secrets and YAML
+
+## Uninstall
 
 ```bash
 make uninstall
 ```
 
-### Status
+This removes symlinks from `~/.claude/` and restores any backed-up files.
-
-```bash
-make status
-```
-
-Shows current symlink state for each component.
-
-### Restart LLMs
-
-```bash
-make restart-llm
-```
-
-Restarts all local LLM services (atlas, forge, swift).
-
-## Project Structure
-
-```
-architecture/
-├── legacy/                     # Historical Claude Code content
-│   ├── old/                    # Early Claude Code structure
-│   ├── old2/                   # Most recent Claude Code structure
-│   ├── docs/                   # Documentation
-│   ├── learnings/              # Governance learnings
-│   └── scripts/                # Bash scripts
-│
-├── .opencode/                  # OpenCode configuration
-│   ├── skills/                 # Reference knowledge (SKILL.md files)
-│   ├── tools/                  # Custom tools (TypeScript/JS)
-│   └── agents/                 # Specialized subagents (AGENT.md files)
-│
-├── Makefile                    # Symlink management
-├── settings.json               # Historical reference (Claude Code)
-└── README.md                   # This file
-```
-
-## Adding Components
-
-### Skills
-
-Create `.opencode/skills/<name>/SKILL.md`:
-
-```markdown
----
-name: skill-name
-description: What this skill does and when to use it
----
-
-# Skill Title
-
-Content goes here...
-```
-
-Skills are auto-discovered by OpenCode and available via the `skill` tool.
-
-### Tools
-
-Create `.opencode/tools/<name>.ts`:
-
-```typescript
-import { tool } from "@opencode-ai/plugin"
-
-export default tool({
-  description: "What this tool does",
-  args: {
-    param: tool.schema.string().describe("Parameter description"),
-  },
-  async execute(args) {
-    // Your implementation
-    return "result"
-  },
-})
-```
-
-Tools are auto-discovered and available to the LLM.
-
-### Agents
-
-Create `.opencode/agents/<name>.md`:
-
-```markdown
----
-description: What this agent does and when to use it
-mode: subagent
-permission:
-  edit: deny
-  bash: deny
----
-
-You are an agent that specializes in...
-```
-
-Agents can be invoked with `@agent-name` or automatically by primary agents.
-
-## Referencing Legacy Content
-
-The `legacy/` folder contains the original Claude Code structure for reference:
-
-- **`legacy/old2/`** - Most recent Claude Code structure with skills, agents, commands
-- **`legacy/old2/manifesto.md`** - Organization vision and beliefs
-- **`legacy/old2/software-architecture.md`** - Architectural patterns and principles
-- **`legacy/old2/learnings/`** - Historical learnings (if any)
-
-These are preserved for historical reference but not actively used by OpenCode.
-
-## Existing OpenCode Configuration
-
-Your global OpenCode configuration is at `~/.config/opencode/opencode.json`. This repository does not manage that file.
-
-The `settings.json` in this repository is kept for historical reference (it was used with Claude Code).
 
 ## License
 

VISION.md

@@ -0,0 +1,102 @@
+# Vision
+
+## The Problem
+
+AI-assisted development is powerful but inconsistent. Claude Code can help with nearly any task, but without structure:
+
+- Workflows vary between sessions and team members
+- Knowledge about good practices stays in heads, not systems
+- Context gets lost when switching between tasks
+- There's no shared vocabulary for common patterns
+
+The gap isn't in AI capability—it's in how we use it.
+
+## The Solution
+
+This project provides a **composable toolkit** for Claude Code that turns ad-hoc AI assistance into structured, repeatable workflows.
+
+Instead of asking Claude to "help with issues" differently each time, you run `/work-issue 42` and get a consistent workflow: fetch the issue, create a branch, plan the work, implement, commit with proper references, and create a PR.
+
+The key insight: **encode your team's best practices into reusable components** that Claude can apply consistently.
+
+## Composable Components
+
+The system is built from three types of components that stack together:
+
+### Skills
+
+Skills are knowledge modules—focused documents that teach Claude how to do something well.
+
+Examples:
+- `issue-writing`: How to structure clear, actionable issues
+- `gitea`: How to use the Gitea CLI for issue/PR management
+- `backlog-grooming`: What makes a healthy backlog
+
+Skills don't do anything on their own. They're building blocks.
+
+### Agents
+
+Agents combine multiple skills into specialized personas that can work autonomously.
+
+The `product-manager` agent combines issue-writing, backlog-grooming, and roadmap-planning skills to handle complex PM tasks. It can explore the codebase, plan features, and create well-structured issues—all with isolated context so it doesn't pollute the main conversation.
+
+Agents enable:
+- **Parallel processing**: Multiple agents can work simultaneously
+- **Context preservation**: Each agent maintains its own focused context
+- **Complex workflows**: Combine skills for multi-step tasks
+
+### Commands
+
+Commands are the user-facing entry points—what you actually invoke.
+
+When you run `/plan-issues add dark mode`, the command:
+1. Understands what you're asking for
+2. Invokes the right agents and skills
+3. Guides you through the workflow with approvals
+4. Takes action (creates issues, PRs, etc.)
+
+Commands make the power of skills and agents accessible through simple invocations.
+
+## Target Users
+
+This toolkit is for:
+
+- **Developers using Claude Code** who want consistent, efficient workflows
+- **Teams** who want to encode and share their best practices
+- **Gitea/Git users** who want seamless issue and PR management integrated into their AI workflow
+
+You should have:
+- Claude Code CLI installed
+- A Gitea instance (or adapt the tooling for GitHub/GitLab)
+- Interest in treating AI assistance as a structured tool, not just a chat interface
+
+## Guiding Principles
+
+### Encode, Don't Repeat
+
+If you find yourself explaining the same thing to Claude repeatedly, that's a skill waiting to be written. Capture it once, use it everywhere.
+
+### Composability Over Complexity
+
+Small, focused components that combine well beat large, monolithic solutions. A skill should do one thing. An agent should serve one role. A command should trigger one workflow.
+
+### Approval Before Action
+
+Destructive or significant actions should require user approval. Commands should show what they're about to do and ask before doing it. This builds trust and catches mistakes.
+
+### Use the Tools to Build the Tools
+
+This project uses its own commands to manage itself. Issues are created with `/create-issue`. Features are planned with `/plan-issues`. PRs are reviewed with `/review-pr`. Dogfooding ensures the tools actually work.
+
+### Progressive Disclosure
+
+Simple things should be simple. `/dashboard` just shows your issues and PRs. But the system supports complex workflows when you need them. Don't require users to understand the full architecture to get value.
+
+## What This Is Not
+
+This is not:
+- A replacement for Claude Code—it enhances it
+- A rigid framework—adapt it to your needs
+- Complete—it grows as we discover new patterns
+
+It's a starting point for treating AI-assisted development as a first-class engineering concern.

agents/code-reviewer/AGENT.md

@@ -0,0 +1,73 @@
+---
+name: code-reviewer
+description: Automated code review of pull requests. Reviews PRs for quality, bugs, security, style, and test coverage. Spawn after PR creation or for on-demand review.
+# Model: sonnet provides good code understanding for review tasks.
+# The structured output format doesn't require opus-level reasoning.
+model: sonnet
+skills: gitea, code-review
+---
+
+You are a code review specialist that provides immediate, structured feedback on pull request changes.
+
+## When Invoked
+
+You will receive a PR number to review. Follow this process:
+
+1. Fetch PR diff using `tea pulls <number> -f diff`
+2. Analyze the diff for issues in these categories:
+   - **Code Quality**: Readability, maintainability, complexity
+   - **Bugs**: Logic errors, edge cases, null checks
+   - **Security**: Injection vulnerabilities, auth issues, data exposure
+   - **Style**: Naming conventions, formatting, consistency
+   - **Test Coverage**: Missing tests, untested edge cases
+3. Generate a structured review comment
+4. Post the review using `tea comment <number> "<review body>"`
+5. **If verdict is LGTM**: Approve with `tea pulls approve <number>`, then auto-merge with `tea pulls merge <number> --style rebase`
+6. **If verdict is NOT LGTM**: Do not merge; leave for the user to address
+
+## Review Comment Format
+
+Post reviews in this structured format:
+
+```markdown
+## AI Code Review
+
+> This is an automated review generated by the code-reviewer agent.
+
+### Summary
+[Brief overall assessment]
+
+### Findings
+
+#### Code Quality
+- [Finding 1]
+- [Finding 2]
+
+#### Potential Bugs
+- [Finding or "No issues found"]
+
+#### Security Concerns
+- [Finding or "No issues found"]
+
+#### Style Notes
+- [Finding or "Consistent with codebase"]
+
+#### Test Coverage
+- [Finding or "Adequate coverage"]
+
+### Verdict
+[LGTM / Needs Changes / Blocking Issues]
+```
+
+## Verdict Criteria
+
+- **LGTM**: No blocking issues, code meets quality standards, ready to merge
+- **Needs Changes**: Minor issues worth addressing before merge
+- **Blocking Issues**: Security vulnerabilities, logic errors, or missing critical functionality
+
+## Guidelines
+
+- Be specific: Reference exact lines and explain *why* something is an issue
+- Be constructive: Suggest alternatives when pointing out problems
+- Be kind: Distinguish between blocking issues and suggestions
+- Acknowledge good solutions when you see them

agents/product-manager/AGENT.md

@@ -0,0 +1,26 @@
+---
+name: product-manager
+description: Backlog management and roadmap planning specialist. Use for batch issue operations, comprehensive backlog reviews, or feature planning that requires codebase exploration.
+# Model: sonnet handles planning and issue-writing well.
+# Tasks follow structured patterns from skills; opus not required.
+model: sonnet
+skills: gitea, issue-writing, backlog-grooming, roadmap-planning
+---
+
+You are a product manager specializing in backlog management and roadmap planning.
+
+## Capabilities
+
+You can:
+- Review and improve existing issues
+- Create new well-structured issues
+- Analyze the backlog for gaps and priorities
+- Plan feature breakdowns
+- Maintain roadmap clarity
+
+## Behavior
+
+- Always fetch current issue state before making changes
+- Ask for approval before creating or modifying issues
+- Provide clear summaries of actions taken
+- Use the gitea skill for all issue/PR operations

commands/create-issue.md

@@ -0,0 +1,19 @@
+---
+description: Create a new Gitea issue. Can create single issues or batch create from a plan.
+argument-hint: [title] or "batch"
+---
+
+# Create Issue(s)
+
+Use the gitea skill.
+
+## Single Issue (default)
+If title provided, create an issue with that title and ask for description.
+
+## Batch Mode
+If $1 is "batch":
+1. Ask user for the plan/direction
+2. Generate list of issues with titles and descriptions
+3. Show for approval
+4. Create each issue
+5. Display all created issue numbers

commands/dashboard.md

@@ -0,0 +1,13 @@
+---
+description: Show dashboard of open issues, PRs awaiting review, and CI status.
+---
+
+# Repository Dashboard
+
+Use the gitea skill.
+
+Fetch and display:
+1. All open issues
+2. All open PRs
+
+Format as tables showing number, title, and author.

commands/groom.md

@@ -0,0 +1,31 @@
+---
+description: Groom and improve issues. Without argument, reviews all open issues. With argument, grooms specific issue.
+argument-hint: [issue-number]
+---
+
+# Groom Issues
+
+Use the gitea, backlog-grooming, and issue-writing skills.
+
+## If issue number provided ($1):
+
+1. **Fetch the issue** details
+2. **Evaluate** against grooming checklist
+3. **Suggest improvements** for:
+   - Title clarity
+   - Description completeness
+   - Acceptance criteria quality
+   - Scope definition
+4. **Ask user** if they want to apply changes
+5. **Update issue** if approved
+
+## If no argument (groom all):
+
+1. **List open issues**
+2. **Review each** against grooming checklist
+3. **Categorize**:
+   - Ready: Well-defined, can start work
+   - Needs work: Missing info or unclear
+   - Stale: No longer relevant
+4. **Present summary** table
+5. **Offer to improve** issues that need work

commands/plan-issues.md

@@ -0,0 +1,34 @@
+---
+description: Plan and create issues for a feature or improvement. Breaks down work into well-structured issues.
+argument-hint: <feature-description>
+---
+
+# Plan Feature: $1
+
+Use the gitea, roadmap-planning, and issue-writing skills.
+
+1. **Understand the feature**: Analyze what "$1" involves
+2. **Explore the codebase** if needed to understand context
+3. **Break down** into discrete, actionable issues:
+   - Each issue should be independently completable
+   - Clear dependencies between issues
+   - Appropriate scope (not too big, not too small)
+
+4. **Present the plan**:
+   ```
+   ## Proposed Issues for: $1
+
+   1. [Title] - Brief description
+      Dependencies: none
+
+   2. [Title] - Brief description
+      Dependencies: #1
+
+   3. [Title] - Brief description
+      Dependencies: #1, #2
+   ```
+
+5. **Ask for approval** before creating issues
+6. **Create issues** in order
+7. **Update dependencies** with actual issue numbers after creation
+8. **Present summary** with links to created issues

commands/retro.md

@@ -0,0 +1,64 @@
+---
+description: Run a retrospective on completed work. Captures learnings and creates improvement issues in the AI repo.
+argument-hint: [task-description]
+---
+
+# Retrospective
+
+Capture learnings from completed AI-assisted work to improve the workflow.
+
+## Process
+
+1. **Gather context**: If $1 is provided, use it as the task description. Otherwise, ask the user what task was just completed.
+
+2. **Reflect on the work**: Ask the user (or summarize from conversation context if obvious):
+   - What friction points were encountered?
+   - What worked well?
+   - Any specific improvement ideas?
+
+3. **Analyze and categorize**: Group learnings into:
+   - **Prompt improvements**: Better instructions for commands/skills
+   - **Missing capabilities**: New commands or skills needed
+   - **Tool issues**: Problems with tea CLI, git, or other tools
+   - **Context gaps**: Missing documentation or skills
+
+4. **Generate improvement issues**: For each actionable improvement, create an issue in the AI repo using:
+
+```bash
+tea issues create -r flowmade-one/ai --title "<title>" --description "<body>"
+```
+
+## Issue Format
+
+Use this structure for retrospective issues:
+
+```markdown
+## Context
+What task triggered this learning (brief).
+
+## Problem / Observation
+What was the friction point or insight.
+
+## Suggested Improvement
+Concrete, actionable change to make.
+
+## Affected Files
+- commands/xxx.md
+- skills/xxx/SKILL.md
+```
+
+## Labels
+
+Add appropriate labels:
+- `retrospective` - Always add this
+- `prompt-improvement` - For command/skill text changes
+- `new-feature` - For new commands/skills
+- `bug` - For things that are broken
+
+## Guidelines
+
+- Be specific and actionable - vague issues won't get fixed
+- One issue per improvement (don't bundle unrelated things)
+- Reference specific commands/skills when relevant
+- Keep issues small and focused
+- Skip creating issues for one-off edge cases that won't recur

commands/review-pr.md

@@ -0,0 +1,22 @@
+---
+description: Review a Gitea pull request. Fetches PR details, diff, and comments.
+argument-hint: <pr-number>
+---
+
+# Review PR #$1
+
+Use the gitea skill.
+
+1. **View PR details** including description and metadata
+2. **Get the diff** to review the changes
+
+Review the changes and provide feedback on:
+- Code quality
+- Potential bugs
+- Test coverage
+- Documentation
+
+Ask the user what action to take:
+- **Merge**: Post review summary as comment, then merge with rebase style
+- **Request changes**: Leave feedback without merging
+- **Comment only**: Add a comment for discussion

commands/roadmap.md

@@ -0,0 +1,31 @@
+---
+description: View current issues as a roadmap. Shows open issues organized by status and dependencies.
+---
+
+# Roadmap View
+
+Use the gitea skill.
+
+1. **Fetch all open issues**
+2. **Analyze dependencies** from issue descriptions
+3. **Categorize issues**:
+   - Blocked: Waiting on other issues
+   - Ready: No blockers, can start
+   - In Progress: Has assignee or WIP label
+4. **Present roadmap** as organized list:
+
+```
+## Ready to Start
+- #5: Add user authentication
+- #8: Create dashboard layout
+
+## In Progress
+- #3: Setup database schema
+
+## Blocked
+- #7: User profile page (blocked by #5)
+- #9: Admin dashboard (blocked by #3, #8)
+```
+
+5. **Highlight** any issues that seem stale or unclear
+6. **Suggest** next actions based on the roadmap state

commands/work-issue.md

@@ -0,0 +1,17 @@
+---
+description: Work on a Gitea issue. Fetches issue details and sets up branch for implementation.
+argument-hint: <issue-number>
+---
+
+# Work on Issue #$1
+
+Use the gitea skill.
+
+1. **View the issue** to understand requirements
+2. **Create a branch**: `git checkout -b issue-$1-<short-kebab-title>`
+3. **Plan**: Use TodoWrite to break down the work based on acceptance criteria
+4. **Implement** the changes
+5. **Commit** with message referencing the issue
+6. **Push** the branch to origin
+7. **Create PR** with title "[Issue #$1] <title>" and body "Closes #$1"
+8. **Auto-review**: Inform the user that auto-review is starting, then spawn the `code-reviewer` agent in background (using `run_in_background: true`) with the PR number

docs/writing-agents.md

@@ -0,0 +1,591 @@
+# Writing Agents
+
+A guide to creating specialized subagents that combine multiple skills for complex, context-isolated tasks.
+
+## What is an Agent?
+
+Agents are **specialized subprocesses** that combine multiple skills into focused personas. Unlike commands (which define workflows) or skills (which encode knowledge), agents are autonomous workers that can handle complex tasks independently.
+
+Think of agents as specialists you can delegate work to. They have their own context, their own expertise (via skills), and they report back when finished.
+
+## File Structure
+
+Agents live in the `agents/` directory, each in its own folder:
+
+```
+agents/
+└── product-manager/
+    └── AGENT.md
+```
+
+### Why AGENT.md?
+
+The uppercase `AGENT.md` filename:
+- Makes the agent file immediately visible in directory listings
+- Follows a consistent convention across all agents
+- Clearly identifies the primary file in an agent folder
+
+### Supporting Files (Optional)
+
+An agent folder can contain additional files if needed:
+
+```
+agents/
+└── code-reviewer/
+    ├── AGENT.md           # Main agent document (required)
+    └── checklists/        # Supporting materials
+        └── security.md
+```
+
+However, prefer keeping everything in `AGENT.md` when possible—agent definitions should be concise.
+
+## Agent Document Structure
+
+A well-structured `AGENT.md` follows this pattern:
+
+```markdown
+# Agent Name
+
+Brief description of what this agent does.
+
+## Skills
+List of skills this agent has access to.
+
+## Capabilities
+What the agent can do—its areas of competence.
+
+## When to Use
+Guidance on when to spawn this agent.
+
+## Behavior
+How the agent should operate—rules and constraints.
+```
+
+All sections are important:
+- **Skills**: Defines what knowledge the agent has
+- **Capabilities**: Tells spawners what to expect
+- **When to Use**: Prevents misuse and guides selection
+- **Behavior**: Sets expectations for operation
+
+## How Agents Combine Skills
+
+Agents gain their expertise by combining multiple skills. Each skill contributes domain knowledge to the agent's overall capability.
+
+### Skill Composition
+
+```
+┌────────────────────────────────────────────────┐
+│           Product Manager Agent                │
+│                                                │
+│  ┌──────────┐  ┌──────────────┐                │
+│  │ gitea  │  │issue-writing │                │
+│  │          │  │              │                │
+│  │ CLI      │  │ Structure    │                │
+│  │ commands │  │ patterns     │                │
+│  └──────────┘  └──────────────┘                │
+│                                                │
+│  ┌──────────────────┐  ┌─────────────────┐     │
+│  │backlog-grooming  │  │roadmap-planning │     │
+│  │                  │  │                 │     │
+│  │ Review           │  │ Feature         │     │
+│  │ checklists       │  │ breakdown       │     │
+│  └──────────────────┘  └─────────────────┘     │
+│                                                │
+└────────────────────────────────────────────────┘
+```
+
+The agent can:
+- Use **gitea** to interact with issues and PRs
+- Apply **issue-writing** patterns when creating content
+- Follow **backlog-grooming** checklists when reviewing
+- Use **roadmap-planning** strategies when breaking down features
+
+### Emergent Capabilities
+
+When skills combine, new capabilities emerge:
+
+| Skills Combined | Emergent Capability |
+|-----------------|---------------------|
+| gitea + issue-writing | Create well-structured issues programmatically |
+| backlog-grooming + issue-writing | Improve existing issues systematically |
+| roadmap-planning + gitea | Plan and create linked issue hierarchies |
+| All four skills | Full backlog management lifecycle |
+
+## Use Cases for Agents
+
+### 1. Parallel Processing
+
+Agents work independently with their own context. Spawn multiple agents to work on separate tasks simultaneously.
+
+```
+Command: /groom (batch mode)
+         │
+         ├─── Spawn Agent: Review issues #1-5
+         │
+         ├─── Spawn Agent: Review issues #6-10
+         │
+         └─── Spawn Agent: Review issues #11-15
+
+         ↓ (agents work in parallel)
+
+Results aggregated by command
+```
+
+**Use when:**
+- Tasks are independent and don't need to share state
+- Workload can be divided into discrete chunks
+- Speed matters more than sequential consistency
+
+### 2. Context Isolation
+
+Each agent maintains separate conversation state. This prevents context pollution when handling complex, unrelated subtasks.
+
+```
+Main Context                    Agent Context
+┌─────────────────┐            ┌─────────────────┐
+│ User working on │            │ Isolated work   │
+│ feature X       │   spawn    │ on backlog      │
+│                 │ ─────────► │ review          │
+│ (preserves      │            │                 │
+│  feature X      │   return   │ (doesn't know   │
+│  context)       │ ◄───────── │  about X)       │
+└─────────────────┘            └─────────────────┘
+```
+
+**Use when:**
+- Subtask requires deep exploration that would pollute main context
+- Work involves many files or concepts unrelated to main task
+- You want clean separation between different concerns
+
+### 3. Complex Workflows
+
+Some workflows are better handled by a specialized agent than by inline execution. Agents can make decisions, iterate, and adapt.
+
+```
+Command: /plan-issues "add user authentication"
+         │
+         └─── Spawn product-manager agent
+                   │
+                   ├── Explore codebase to understand structure
+                   ├── Research authentication patterns
+                   ├── Design issue breakdown
+                   ├── Create issues in dependency order
+                   └── Return summary to command
+```
+
+**Use when:**
+- Task requires iterative decision-making
+- Workflow has many steps that depend on intermediate results
+- Specialist expertise (via combined skills) adds value
+
+### 4. Autonomous Exploration
+
+Agents can explore codebases independently, building understanding without polluting the main conversation.
+
+**Use when:**
+- You need to understand a new part of the codebase
+- Exploration might involve many file reads and searches
+- Results should be summarized, not shown in full
+
+## When to Use an Agent vs Direct Skill Invocation
+
+### Use Direct Skill Invocation When:
+
+- **Simple, single-skill task**: Writing one issue doesn't need an agent
+- **Main context is relevant**: The current conversation context helps
+- **Quick reference needed**: Just need to check a pattern or command
+- **Sequential workflow**: Command can orchestrate step-by-step
+
+Example: Creating a single issue with `/create-issue`
+```
+Command reads issue-writing skill directly
+         │
+         └── Creates one issue following patterns
+```
+
+### Use an Agent When:
+
+- **Multiple skills needed together**: Complex tasks benefit from composition
+- **Context isolation required**: Don't want to pollute main conversation
+- **Parallel execution possible**: Can divide and conquer
+- **Autonomous exploration needed**: Agent can figure things out independently
+- **Specialist persona helps**: "Product manager" framing improves outputs
+
+Example: Grooming entire backlog with `/groom`
+```
+Command spawns product-manager agent
+         │
+         └── Agent iterates through all issues
+             using multiple skills
+```
+
+### Decision Matrix
+
+| Scenario | Agent? | Reason |
+|----------|--------|--------|
+| Create one issue | No | Single skill, simple task |
+| Review 20 issues | Yes | Batch processing, isolation |
+| Quick CLI lookup | No | Just need gitea reference |
+| Plan new feature | Yes | Multiple skills, exploration |
+| Fix issue title | No | Trivial edit |
+| Reorganize backlog | Yes | Complex, multi-skill workflow |
+
+## Annotated Example: Product Manager Agent
+
+Let's examine the `product-manager` agent in detail:
+
+```markdown
+# Product Manager Agent
+
+Specialized agent for backlog management and roadmap planning.
+```
+
+**The opening** identifies the agent's role clearly. "Product Manager" is a recognizable persona that sets expectations.
+
+```markdown
+## Skills
+
+- gitea
+- issue-writing
+- backlog-grooming
+- roadmap-planning
+```
+
+**Skills section** lists all knowledge the agent has access to. These skills are loaded into the agent's context when spawned. The combination enables:
+- Reading/writing issues (gitea)
+- Creating quality content (issue-writing)
+- Evaluating existing issues (backlog-grooming)
+- Planning work strategically (roadmap-planning)
+
+```markdown
+## Capabilities
+
+This agent can:
+- Review and improve existing issues
+- Create new well-structured issues
+- Analyze the backlog for gaps and priorities
+- Plan feature breakdowns
+- Maintain roadmap clarity
+```
+
+**Capabilities section** tells spawners what to expect. Each capability maps to skill combinations:
+- "Review and improve" = backlog-grooming + issue-writing
+- "Create new issues" = gitea + issue-writing
+- "Analyze backlog" = backlog-grooming + roadmap-planning
+- "Plan breakdowns" = roadmap-planning + issue-writing
+
+```markdown
+## When to Use
+
+Spawn this agent for:
+- Batch operations on multiple issues
+- Comprehensive backlog reviews
+- Feature planning that requires codebase exploration
+- Complex issue creation with dependencies
+```
+
+**When to Use section** guides appropriate usage. Note the criteria:
+- "Batch operations" → Parallel/isolation benefit
+- "Comprehensive reviews" → Complex workflow benefit
+- "Requires exploration" → Context isolation benefit
+- "Complex with dependencies" → Multi-skill benefit
+
+```markdown
+## Behavior
+
+- Always fetches current issue state before making changes
+- Asks for approval before creating or modifying issues
+- Provides clear summaries of actions taken
+- Uses the tea CLI for all Forgejo operations
+```
+
+**Behavior section** sets operational rules. These ensure:
+- Accuracy: Fetches current state, doesn't assume
+- Safety: Asks before acting
+- Transparency: Summarizes what happened
+- Consistency: Uses standard tooling
+
+## Naming Conventions
+
+### Agent Folder Names
+
+- Use **kebab-case**: `product-manager`, `code-reviewer`
+- Name by **role or persona**: what the agent "is"
+- Keep **recognizable**: familiar roles are easier to understand
+
+Good names:
+- `product-manager` - Recognizable role
+- `code-reviewer` - Clear function
+- `security-auditor` - Specific expertise
+- `documentation-writer` - Focused purpose
+
+Avoid:
+- `helper` - Too vague
+- `do-stuff` - Not a role
+- `issue-thing` - Not recognizable
+
+### Agent Titles
+
+The H1 title in `AGENT.md` should be the role name in Title Case:
+
+| Folder | Title |
+|--------|-------|
+| `product-manager` | Product Manager Agent |
+| `code-reviewer` | Code Reviewer Agent |
+| `security-auditor` | Security Auditor Agent |
+
+## Model Selection
+
+Agents can specify which Claude model to use via the `model` field in YAML frontmatter. Choosing the right model balances capability, speed, and cost.
+
+### Available Models
+
+| Model | Characteristics | Best For |
+|-------|-----------------|----------|
+| `haiku` | Fastest, most cost-effective | Simple structured tasks, formatting, basic transformations |
+| `sonnet` | Balanced speed and capability | Most agent tasks, code review, issue management |
+| `opus` | Most capable, best reasoning | Complex analysis, architectural decisions, nuanced judgment |
+| `inherit` | Uses parent context's model | When agent should match caller's capability level |
+
+### Decision Matrix
+
+| Agent Task Type | Recommended Model | Reasoning |
+|-----------------|-------------------|-----------|
+| Structured output formatting | `haiku` | Pattern-following, no complex reasoning |
+| Code review (style/conventions) | `sonnet` | Needs code understanding, not deep analysis |
+| Security vulnerability analysis | `opus` | Requires nuanced judgment, high stakes |
+| Issue triage and labeling | `haiku` or `sonnet` | Mostly classification tasks |
+| Feature planning and breakdown | `sonnet` or `opus` | Needs strategic thinking |
+| Batch processing (many items) | `haiku` or `sonnet` | Speed and cost matter at scale |
+| Architectural exploration | `opus` | Complex reasoning about tradeoffs |
+
+### Examples
+
+These examples show recommended model configurations for different agent types:
+
+**Code Reviewer Agent** - Use `sonnet`:
+```yaml
+---
+name: code-reviewer
+model: sonnet
+skills: gitea, code-review
+---
+```
+Code review requires understanding code patterns and conventions but rarely needs the deepest reasoning. Sonnet provides good balance.
+
+**Security Auditor Agent** (hypothetical) - Use `opus`:
+```yaml
+---
+name: security-auditor
+model: opus
+skills: code-review  # would add security-specific skills
+---
+```
+Security analysis requires careful, nuanced judgment where missing issues have real consequences. Worth the extra capability.
+
+**Formatting Agent** (hypothetical) - Use `haiku`:
+```yaml
+---
+name: markdown-formatter
+model: haiku
+skills: documentation
+---
+```
+Pure formatting tasks follow patterns and don't require complex reasoning. Haiku is fast and sufficient.
+
+### Best Practices for Model Selection
+
+1. **Start with `sonnet`** - It handles most agent tasks well
+2. **Use `haiku` for volume** - When processing many items, speed and cost add up
+3. **Reserve `opus` for judgment** - Use when errors are costly or reasoning is complex
+4. **Avoid `inherit` by default** - Make a deliberate choice; `inherit` obscures the decision
+5. **Consider the stakes** - Higher consequence tasks warrant more capable models
+6. **Test with real tasks** - Verify the chosen model performs adequately
+
+### When to Use `inherit`
+
+The `inherit` option has legitimate uses:
+
+- **Utility agents**: Small helpers that should match their caller's capability
+- **Delegation chains**: When an agent spawns sub-agents that should stay consistent
+- **Testing/development**: When you want to control model from the top level
+
+However, most production agents should specify an explicit model.
+
+## Best Practices
+
+### 1. Choose Skills Deliberately
+
+Include only skills the agent needs. More skills = more context = potential confusion.
+
+**Too many skills:**
+```markdown
+## Skills
+- gitea
+- issue-writing
+- backlog-grooming
+- roadmap-planning
+- code-review
+- testing
+- documentation
+- deployment
+```
+
+**Right-sized:**
+```markdown
+## Skills
+- gitea
+- issue-writing
+- backlog-grooming
+- roadmap-planning
+```
+
+### 2. Define Clear Boundaries
+
+Agents should know what they can and cannot do.
+
+**Vague:**
+```markdown
+## Capabilities
+This agent can help with project management.
+```
+
+**Clear:**
+```markdown
+## Capabilities
+This agent can:
+- Review and improve existing issues
+- Create new well-structured issues
+- Analyze the backlog for gaps
+
+This agent cannot:
+- Merge pull requests
+- Deploy code
+- Make architectural decisions
+```
+
+### 3. Set Behavioral Guardrails
+
+Prevent agents from causing problems by setting explicit rules.
+
+**Important behaviors to specify:**
+- When to ask for approval
+- What to do before making changes
+- How to report results
+- Error handling expectations
+
+### 4. Match Persona to Purpose
+
+The agent's name and description should align with its skills and capabilities.
+
+**Mismatched:**
+```markdown
+# Security Agent
+
+## Skills
+- issue-writing
+- documentation
+```
+
+**Aligned:**
+```markdown
+# Security Auditor Agent
+
+## Skills
+- security-scanning
+- vulnerability-assessment
+- code-review
+```
+
+### 5. Keep Agents Focused
+
+One agent = one role. If an agent does too many unrelated things, split it.
+
+**Too broad:**
+```markdown
+# Everything Agent
+Handles issues, code review, deployment, and customer support.
+```
+
+**Focused:**
+```markdown
+# Product Manager Agent
+Specialized for backlog management and roadmap planning.
+```
+
+## When to Create a New Agent
+
+Create an agent when you need:
+
+1. **Role-based expertise**: A recognizable persona improves outputs
+2. **Skill composition**: Multiple skills work better together
+3. **Context isolation**: Work shouldn't pollute main conversation
+4. **Parallel capability**: Tasks can run independently
+5. **Autonomous operation**: Agent should figure things out on its own
+
+### Signs You Need a New Agent
+
+- Commands repeatedly spawn similar skill combinations
+- Tasks require deep exploration that pollutes context
+- Work benefits from a specialist "persona"
+- Batch processing would help
+
+### Signs You Don't Need a New Agent
+
+- Single skill is sufficient
+- Task is simple and sequential
+- Main context is helpful, not harmful
+- No clear persona or role emerges
+
+## Agent Lifecycle
+
+### 1. Design
+
+Define the agent's role:
+- What persona makes sense?
+- Which skills does it need?
+- What can it do (and not do)?
+- When should it be spawned?
+
+### 2. Implement
+
+Create the agent file:
+- Clear name and description
+- Appropriate skill list
+- Specific capabilities
+- Usage guidance
+- Behavioral rules
+
+### 3. Integrate
+
+Connect the agent to workflows:
+- Update commands that should spawn it
+- Document in ARCHITECTURE.md
+- Test with real tasks
+
+### 4. Refine
+
+Improve based on usage:
+- Add/remove skills as needed
+- Clarify capabilities
+- Strengthen behavioral rules
+- Update documentation
+
+## Checklist: Before Submitting a New Agent
+
+- [ ] File is at `agents/<name>/AGENT.md`
+- [ ] Name follows kebab-case convention
+- [ ] Agent has a clear, recognizable role
+- [ ] Skills list is deliberate (not too many, not too few)
+- [ ] Model selection is deliberate (not just `inherit` by default)
+- [ ] Capabilities are specific and achievable
+- [ ] "When to Use" guidance is clear
+- [ ] Behavioral rules prevent problems
+- [ ] Agent is referenced by at least one command
+- [ ] ARCHITECTURE.md is updated
+
+## See Also
+
+- [ARCHITECTURE.md](../ARCHITECTURE.md): How agents fit into the overall system
+- [writing-skills.md](writing-skills.md): Creating the skills that agents use
+- [VISION.md](../VISION.md): The philosophy behind composable components

docs/writing-commands.md

@@ -0,0 +1,655 @@
+# Writing Commands
+
+A guide to creating user-facing entry points that trigger workflows.
+
+## What is a Command?
+
+Commands are **user-facing entry points** that trigger workflows. Unlike skills (which encode knowledge) or agents (which execute tasks autonomously), commands define *what* to do—they orchestrate the workflow that users invoke directly.
+
+Think of commands as the interface between users and the system. Users type `/work-issue 42` and the command defines the entire workflow: fetch issue, create branch, implement, commit, push, create PR.
+
+## File Structure
+
+Commands live directly in the `commands/` directory as markdown files:
+
+```
+commands/
+├── work-issue.md
+├── dashboard.md
+├── review-pr.md
+├── create-issue.md
+├── groom.md
+├── roadmap.md
+└── plan-issues.md
+```
+
+### Why Flat Files?
+
+Unlike skills and agents (which use folders), commands are single files because:
+- Commands are self-contained workflow definitions
+- No supporting files needed
+- Simple naming: `/work-issue` maps to `work-issue.md`
+
+## Command Document Structure
+
+A well-structured command file has two parts:
+
+### 1. Frontmatter (YAML Header)
+
+```yaml
+---
+description: Brief description shown in command listings
+argument-hint: <required-arg> [optional-arg]
+---
+```
+
+| Field | Purpose | Required |
+|-------|---------|----------|
+| `description` | One-line summary for help/listings | Yes |
+| `argument-hint` | Shows expected arguments | If arguments needed |
+
+### 2. Body (Markdown Instructions)
+
+```markdown
+# Command Title
+
+Brief intro if needed.
+
+1. **Step one**: What to do
+2. **Step two**: What to do next
+...
+```
+
+The body contains the workflow steps that Claude follows when the command is invoked.
+
+## Complete Command Example
+
+```markdown
+---
+description: Work on a Gitea issue. Fetches issue details and sets up branch.
+argument-hint: <issue-number>
+---
+
+# Work on Issue #$1
+
+Use the gitea skill.
+
+1. **View the issue** to understand requirements
+2. **Create a branch**: `git checkout -b issue-$1-<short-kebab-title>`
+3. **Plan**: Use TodoWrite to break down the work
+4. **Implement** the changes
+5. **Commit** with message referencing the issue
+6. **Push** the branch to origin
+7. **Create PR** with title "[Issue #$1] <title>" and body "Closes #$1"
+```
+
+## Argument Handling
+
+Commands can accept arguments from the user. Arguments are passed via positional variables: `$1`, `$2`, etc.
+
+### The ARGUMENTS Pattern
+
+When users invoke a command with arguments:
+```
+/work-issue 42
+```
+
+The system provides the arguments via the `$1`, `$2`, etc. placeholders in the command body:
+```markdown
+# Work on Issue #$1
+1. **View the issue** to understand requirements
+```
+
+Becomes:
+```markdown
+# Work on Issue #42
+1. **View the issue** to understand requirements
+```
+
+### Argument Hints
+
+Use `argument-hint` in frontmatter to document expected arguments:
+
+| Pattern | Meaning |
+|---------|---------|
+| `<arg>` | Required argument |
+| `[arg]` | Optional argument |
+| `<arg1> <arg2>` | Multiple required |
+| `[arg1] [arg2]` | Multiple optional |
+| `<required> [optional]` | Mix of both |
+
+Examples:
+```yaml
+argument-hint: <issue-number>           # One required
+argument-hint: [issue-number]           # One optional
+argument-hint: <title> [description]    # Required + optional
+argument-hint: [title] or "batch"       # Choice of modes
+```
+
+### Handling Optional Arguments
+
+Commands often have different behavior based on whether arguments are provided:
+
+```markdown
+---
+description: Groom issues. Without argument, reviews all. With argument, grooms specific issue.
+argument-hint: [issue-number]
+---
+
+# Groom Issues
+
+Use the gitea skill.
+
+## If issue number provided ($1):
+1. **Fetch the issue** details
+2. **Evaluate** against checklist
+...
+
+## If no argument (groom all):
+1. **List open issues**
+2. **Review each** against checklist
+...
+```
+
+### Multiple Modes
+
+Some commands support distinct modes based on the first argument:
+
+```markdown
+---
+description: Create issues. Single or batch mode.
+argument-hint: [title] or "batch"
+---
+
+# Create Issue(s)
+
+Use the gitea skill.
+
+## Single Issue (default)
+If title provided, create an issue with that title.
+
+## Batch Mode
+If $1 is "batch":
+1. Ask user for the plan
+2. Generate list of issues
+3. Show for approval
+4. Create each issue
+```
+
+## Invoking Skills
+
+Commands reference skills by name to gain domain knowledge. When a skill is referenced, Claude reads the skill file before proceeding.
+
+### Explicit Reference
+
+```markdown
+# Groom Issues
+
+Use the **gitea**, **backlog-grooming**, and **issue-writing** skills.
+
+1. **Fetch the issue** details
+2. **Evaluate** against grooming checklist
+...
+```
+
+The phrase "Use the gitea, backlog-grooming and issue-writing skills" tells Claude to read and apply knowledge from those skill files.
+
+### Skill-Based Approach
+
+Commands should reference skills rather than embedding CLI commands directly:
+
+```markdown
+1. **Fetch the issue** details
+```
+
+This relies on the `gitea` skill to provide the CLI knowledge.
+
+### When to Reference Skills
+
+| Reference explicitly | Reference implicitly |
+|---------------------|---------------------|
+| Core methodology is needed | Just using a tool |
+| Quality standards matter | Simple operations |
+| Patterns should be followed | Well-known commands |
+
+## Invoking Agents
+
+Commands can spawn agents for complex subtasks that benefit from skill composition or context isolation.
+
+### Spawning Agents
+
+```markdown
+For comprehensive backlog review, spawn the **product-manager** agent to:
+- Review all open issues
+- Categorize by readiness
+- Propose improvements
+```
+
+### When to Spawn Agents
+
+Spawn an agent when the command needs:
+- **Parallel processing**: Multiple independent tasks
+- **Context isolation**: Deep exploration that would pollute main context
+- **Skill composition**: Multiple skills working together
+- **Autonomous operation**: Let the agent figure out details
+
+### Example: Conditional Agent Spawning
+
+```markdown
+# Groom Issues
+
+## If no argument (groom all):
+For large backlogs (>10 issues), consider spawning the
+product-manager agent to handle the review autonomously.
+```
+
+## Interactive Patterns
+
+Commands often require user interaction for confirmation, choices, or input.
+
+### Approval Workflows
+
+Always ask for approval before significant actions:
+
+```markdown
+5. **Ask for approval** before creating issues
+6. **Create issues** in order
+```
+
+Common approval points:
+- Before creating/modifying resources (issues, PRs, files)
+- Before executing destructive operations
+- When presenting a plan that will be executed
+
+### Presenting Choices
+
+When the command leads to multiple possible actions:
+
+```markdown
+Ask the user what action to take:
+- **Merge**: Approve and merge the PR
+- **Request changes**: Leave feedback without merging
+- **Comment only**: Add a comment for discussion
+```
+
+### Gathering Input
+
+Some commands need to gather information from the user:
+
+```markdown
+## Batch Mode
+If $1 is "batch":
+1. **Ask user** for the plan/direction
+2. Generate list of issues with titles and descriptions
+3. Show for approval
+```
+
+### Presenting Results
+
+Commands should clearly show what was done:
+
+```markdown
+7. **Update dependencies** with actual issue numbers after creation
+8. **Present summary** with links to created issues
+```
+
+Good result presentations include:
+- Tables for lists of items
+- Links for created resources
+- Summaries of changes made
+- Next step suggestions
+
+## Annotated Examples
+
+Let's examine existing commands to understand effective patterns.
+
+### Example 1: work-issue (Linear Workflow)
+
+```markdown
+---
+description: Work on a Gitea issue. Fetches issue details and sets up branch.
+argument-hint: <issue-number>
+---
+
+# Work on Issue #$1
+
+Use the gitea skill.
+
+1. **View the issue** to understand requirements
+2. **Create a branch**: `git checkout -b issue-$1-<short-kebab-title>`
+3. **Plan**: Use TodoWrite to break down the work
+4. **Implement** the changes
+5. **Commit** with message referencing the issue
+6. **Push** the branch to origin
+7. **Create PR** with title "[Issue #$1] <title>" and body "Closes #$1"
+```
+
+**Key patterns:**
+- **Linear workflow**: Clear numbered steps in order
+- **Required argument**: `<issue-number>` means must provide
+- **Variable substitution**: `$1` used throughout
+- **Skill reference**: Uses gitea skill for CLI knowledge
+- **Git integration**: Branch and push steps specified
+
+### Example 2: dashboard (No Arguments)
+
+```markdown
+---
+description: Show dashboard of open issues, PRs awaiting review, and CI status.
+---
+
+# Repository Dashboard
+
+Use the gitea skill.
+
+Fetch and display:
+1. All open issues
+2. All open PRs
+
+Format as tables showing issue/PR number, title, and author.
+```
+
+**Key patterns:**
+- **No argument-hint**: Command takes no arguments
+- **Output formatting**: Specifies how to present results
+- **Aggregation**: Combines multiple data sources
+- **Simple workflow**: Just fetch and display
+
+### Example 3: groom (Optional Argument with Modes)
+
+```markdown
+---
+description: Groom and improve issues. Without argument, reviews all. With argument, grooms specific issue.
+argument-hint: [issue-number]
+---
+
+# Groom Issues
+
+Use the gitea, backlog-grooming, and issue-writing skills.
+
+## If issue number provided ($1):
+1. **Fetch the issue** details
+2. **Evaluate** against grooming checklist
+3. **Suggest improvements** for:
+   - Title clarity
+   - Description completeness
+   - Acceptance criteria quality
+4. **Ask user** if they want to apply changes
+5. **Update issue** if approved
+
+## If no argument (groom all):
+1. **List open issues**
+2. **Review each** against grooming checklist
+3. **Categorize**: Ready / Needs work / Stale
+4. **Present summary** table
+5. **Offer to improve** issues that need work
+```
+
+**Key patterns:**
+- **Optional argument**: `[issue-number]` with brackets
+- **Mode switching**: Different behavior based on argument presence
+- **Explicit skill reference**: "Use the gitea, backlog-grooming and issue-writing skills"
+- **Approval workflow**: "Ask user if they want to apply changes"
+- **Categorization**: Groups items for presentation
+
+### Example 4: plan-issues (Complex Workflow)
+
+```markdown
+---
+description: Plan and create issues for a feature. Breaks down work into well-structured issues.
+argument-hint: <feature-description>
+---
+
+# Plan Feature: $1
+
+Use the gitea, roadmap-planning, and issue-writing skills.
+
+1. **Understand the feature**: Analyze what "$1" involves
+2. **Explore the codebase** if needed to understand context
+3. **Break down** into discrete, actionable issues
+4. **Present the plan**:
+   ```
+   ## Proposed Issues for: $1
+
+   1. [Title] - Brief description
+      Dependencies: none
+   ...
+   ```
+5. **Ask for approval** before creating issues
+6. **Create issues** in order
+7. **Update dependencies** with actual issue numbers
+8. **Present summary** with links to created issues
+```
+
+**Key patterns:**
+- **Multi-skill composition**: References three skills together
+- **Codebase exploration**: May need to understand context
+- **Structured output**: Template for presenting the plan
+- **Two-phase execution**: Plan first, then execute after approval
+- **Dependency management**: Creates issues in order, updates references
+
+### Example 5: review-pr (Action Choices)
+
+```markdown
+---
+description: Review a Gitea pull request. Fetches PR details, diff, and comments.
+argument-hint: <pr-number>
+---
+
+# Review PR #$1
+
+Use the gitea skill.
+
+1. **View PR details** including description and metadata
+2. **Get the diff** to review the changes
+
+Review the changes and provide feedback on:
+- Code quality
+- Potential bugs
+- Test coverage
+- Documentation
+
+Ask the user what action to take:
+- **Merge**: Approve and merge the PR
+- **Request changes**: Leave feedback without merging
+- **Comment only**: Add a comment for discussion
+```
+
+**Key patterns:**
+- **Information gathering**: Fetches context before analysis
+- **Review criteria**: Checklist of what to examine
+- **Action menu**: Clear choices with explanations
+- **User decides outcome**: Command presents options, user chooses
+
+## Naming Conventions
+
+### Command File Names
+
+- Use **kebab-case**: `work-issue.md`, `plan-issues.md`
+- Use **verbs or verb phrases**: Commands are actions
+- Be **concise**: 1-3 words is ideal
+- Match the **invocation**: `/work-issue` → `work-issue.md`
+
+Good names:
+- `work-issue` - Action + target
+- `dashboard` - What it shows
+- `review-pr` - Action + target
+- `plan-issues` - Action + target
+- `groom` - Action (target implied)
+
+Avoid:
+- `issue-work` - Noun-first is awkward
+- `do-stuff` - Too vague
+- `manage-issues-and-prs` - Too long
+
+### Command Titles
+
+The H1 title can be more descriptive than the filename:
+
+| Filename | Title |
+|----------|-------|
+| `work-issue.md` | Work on Issue #$1 |
+| `dashboard.md` | Repository Dashboard |
+| `plan-issues.md` | Plan Feature: $1 |
+
+## Best Practices
+
+### 1. Design Clear Workflows
+
+Each step should be unambiguous:
+
+**Vague:**
+```markdown
+1. Handle the issue
+2. Do the work
+3. Finish up
+```
+
+**Clear:**
+```markdown
+1. **View the issue** to understand requirements
+2. **Create a branch**: `git checkout -b issue-$1-<title>`
+3. **Plan**: Use TodoWrite to break down the work
+```
+
+### 2. Show Don't Tell
+
+Include actual commands and expected outputs:
+
+**Telling:**
+```markdown
+List the open issues.
+```
+
+**Showing:**
+```markdown
+Fetch all open issues and format as table:
+| # | Title | Author |
+|---|-------|--------|
+```
+
+### 3. Always Ask Before Acting
+
+Never modify resources without user approval:
+
+```markdown
+4. **Present plan** for approval
+5. **If approved**, create the issues
+```
+
+### 4. Handle Edge Cases
+
+Consider what happens when things are empty or unexpected:
+
+```markdown
+## If no argument (groom all):
+1. **List open issues**
+2. If no issues found, report "No open issues to groom"
+3. Otherwise, **review each** against checklist
+```
+
+### 5. Provide Helpful Output
+
+End with useful information:
+
+```markdown
+8. **Present summary** with:
+   - Links to created issues
+   - Dependency graph
+   - Suggested next steps
+```
+
+### 6. Keep Commands Focused
+
+One command = one workflow. If doing multiple unrelated things, split into separate commands.
+
+**Too broad:**
+```markdown
+# Manage Everything
+Handle issues, PRs, deployments, and documentation...
+```
+
+**Focused:**
+```markdown
+# Review PR #$1
+Review and take action on a pull request...
+```
+
+## When to Create a Command
+
+Create a command when you have:
+
+1. **Repeatable workflow**: Same steps used multiple times
+2. **User-initiated action**: User explicitly triggers it
+3. **Clear start and end**: Workflow has defined boundaries
+4. **Consistent behavior needed**: Should work the same every time
+
+### Signs You Need a New Command
+
+- You're explaining the same workflow repeatedly
+- Users would benefit from a single invocation
+- Multiple tools need orchestration
+- Approval checkpoints are needed
+
+### Signs You Don't Need a Command
+
+- It's a one-time action
+- No workflow orchestration needed
+- A skill reference is sufficient
+- An agent could handle it autonomously
+
+## Command Lifecycle
+
+### 1. Design
+
+Define the workflow:
+- What triggers it?
+- What arguments does it need?
+- What steps are involved?
+- Where are approval points?
+- What does success look like?
+
+### 2. Implement
+
+Create the command file:
+- Clear frontmatter
+- Step-by-step workflow
+- Skill references where needed
+- Approval checkpoints
+- Output formatting
+
+### 3. Test
+
+Verify the workflow:
+- Run with typical arguments
+- Test edge cases (no args, invalid args)
+- Confirm approval points work
+- Check output formatting
+
+### 4. Document
+
+Update references:
+- Add to ARCHITECTURE.md table
+- Update README if user-facing
+- Note any skill/agent dependencies
+
+## Checklist: Before Submitting a New Command
+
+- [ ] File is at `commands/<name>.md`
+- [ ] Name follows kebab-case verb convention
+- [ ] Frontmatter includes description
+- [ ] Frontmatter includes argument-hint (if arguments needed)
+- [ ] Workflow steps are clear and numbered
+- [ ] Commands and tools are specified explicitly
+- [ ] Skills are referenced where methodology matters
+- [ ] Approval points exist before significant actions
+- [ ] Edge cases are handled (no data, invalid input)
+- [ ] Output formatting is specified
+- [ ] ARCHITECTURE.md is updated with new command
+
+## See Also
+
+- [ARCHITECTURE.md](../ARCHITECTURE.md): How commands fit into the overall system
+- [writing-skills.md](writing-skills.md): Creating skills that commands reference
+- [writing-agents.md](writing-agents.md): Creating agents that commands spawn
+- [VISION.md](../VISION.md): The philosophy behind composable components

docs/writing-skills.md

@@ -0,0 +1,445 @@
+# Writing Skills
+
+A guide to creating reusable knowledge modules for the Claude Code AI workflow system.
+
+## What is a Skill?
+
+Skills are **knowledge modules**—focused documents that teach Claude how to do something well. Unlike commands (which define workflows) or agents (which execute tasks), skills are passive: they encode domain expertise, patterns, and best practices that can be referenced when needed.
+
+Think of skills as the "how-to guides" that inform Claude's work. A skill doesn't act on its own—it provides the knowledge that commands and agents use to complete their tasks effectively.
+
+## File Structure
+
+Skills live in the `skills/` directory, each in its own folder:
+
+```
+skills/
+├── gitea/
+│   └── SKILL.md
+├── issue-writing/
+│   └── SKILL.md
+├── backlog-grooming/
+│   └── SKILL.md
+└── roadmap-planning/
+    └── SKILL.md
+```
+
+### Why SKILL.md?
+
+The uppercase `SKILL.md` filename:
+- Makes the skill file immediately visible in directory listings
+- Follows a consistent convention across all skills
+- Clearly identifies the primary file in a skill folder
+
+### Supporting Files (Optional)
+
+A skill folder can contain additional files if needed:
+
+```
+skills/
+└── complex-skill/
+    ├── SKILL.md           # Main skill document (required)
+    ├── templates/         # Template files
+    │   └── example.md
+    └── examples/          # Extended examples
+        └── case-study.md
+```
+
+However, prefer keeping everything in `SKILL.md` when possible—it's easier to maintain and reference.
+
+## Skill Document Structure
+
+A well-structured `SKILL.md` follows this pattern:
+
+```markdown
+# Skill Name
+
+Brief description of what this skill covers.
+
+## Core Concepts
+Explain the fundamental ideas Claude needs to understand.
+
+## Patterns and Templates
+Provide reusable structures and formats.
+
+## Guidelines
+List rules, best practices, and quality standards.
+
+## Examples
+Show concrete illustrations of the skill in action.
+
+## Common Mistakes
+Document pitfalls to avoid.
+
+## Reference
+Quick-reference tables, checklists, or commands.
+```
+
+Not every skill needs all sections—include what's relevant. Some skills are primarily patterns (like `issue-writing`), others are reference-heavy (like `gitea`).
+
+## How Skills are Loaded
+
+Skills are loaded by **explicit reference**. When a command or agent mentions a skill by name, Claude reads the skill file to gain that knowledge.
+
+### Referenced by Commands
+
+Commands reference skills in their instructions:
+
+```markdown
+# Groom Issues
+
+Use the **backlog-grooming** and **issue-writing** skills to review and improve issues.
+
+1. Fetch open issues...
+```
+
+When this command runs, Claude reads both referenced skills before proceeding.
+
+### Referenced by Agents
+
+Agents list their skills explicitly:
+
+```markdown
+# Product Manager Agent
+
+## Skills
+- gitea
+- issue-writing
+- backlog-grooming
+- roadmap-planning
+```
+
+When spawned, the agent has access to all listed skills as part of its context.
+
+### Skills Can Reference Other Skills
+
+Skills can mention other skills for related knowledge:
+
+```markdown
+# Roadmap Planning
+
+...
+
+When creating issues, follow the patterns in the **issue-writing** skill.
+Use **gitea** commands to create the issues.
+```
+
+This creates a natural knowledge hierarchy without duplicating content.
+
+## Naming Conventions
+
+### Skill Folder Names
+
+- Use **kebab-case**: `issue-writing`, `backlog-grooming`
+- Be **descriptive**: name should indicate the skill's domain
+- Be **concise**: 2-3 words is ideal
+- Avoid generic names: `utils`, `helpers`, `common`
+
+Good names:
+- `gitea` - Tool-specific knowledge
+- `issue-writing` - Activity-focused
+- `backlog-grooming` - Process-focused
+- `roadmap-planning` - Task-focused
+
+### Skill Titles
+
+The H1 title in `SKILL.md` should match the folder name in Title Case:
+
+| Folder | Title |
+|--------|-------|
+| `gitea` | Forgejo CLI (fj) |
+| `issue-writing` | Issue Writing |
+| `backlog-grooming` | Backlog Grooming |
+| `roadmap-planning` | Roadmap Planning |
+
+## Best Practices
+
+### 1. Keep Skills Focused
+
+Each skill should cover **one domain, one concern**. If your skill document is getting long or covers multiple unrelated topics, consider splitting it.
+
+**Too broad:**
+```markdown
+# Project Management
+How to manage issues, PRs, releases, and documentation...
+```
+
+**Better:**
+```markdown
+# Issue Writing
+How to write clear, actionable issues.
+```
+
+### 2. Be Specific, Not Vague
+
+Provide concrete patterns, not abstract principles.
+
+**Vague:**
+```markdown
+## Writing Good Titles
+Titles should be clear and descriptive.
+```
+
+**Specific:**
+```markdown
+## Writing Good Titles
+- Start with action verb: "Add", "Fix", "Update", "Remove"
+- Be specific: "Add user authentication" not "Auth stuff"
+- Keep under 60 characters
+```
+
+### 3. Include Actionable Examples
+
+Every guideline should have an example showing what it looks like in practice.
+
+```markdown
+### Acceptance Criteria
+
+Good criteria are:
+- **Specific**: "User sees error message" not "Handle errors"
+- **Testable**: Can verify pass/fail
+- **User-focused**: What the user experiences
+
+Examples:
+- [ ] Login form validates email format before submission
+- [ ] Invalid credentials show "Invalid email or password" message
+- [ ] Successful login redirects to dashboard
+```
+
+### 4. Use Templates for Repeatability
+
+When the skill involves creating structured content, provide copy-paste templates:
+
+```markdown
+### Feature Request Template
+
+\```markdown
+## Summary
+What feature and why it's valuable.
+
+## Acceptance Criteria
+- [ ] Criterion 1
+- [ ] Criterion 2
+
+## Context
+Additional background or references.
+\```
+```
+
+### 5. Include Checklists for Verification
+
+Checklists help ensure consistent quality:
+
+```markdown
+## Grooming Checklist
+
+For each issue, verify:
+- [ ] Starts with action verb
+- [ ] Has acceptance criteria
+- [ ] Scope is clear
+- [ ] Dependencies identified
+```
+
+### 6. Document Common Mistakes
+
+Help avoid pitfalls by documenting what goes wrong:
+
+```markdown
+## Common Mistakes
+
+### Vague Titles
+- Bad: "Fix bug"
+- Good: "Fix login form validation on empty email"
+
+### Missing Acceptance Criteria
+Every issue needs specific, testable criteria.
+```
+
+### 7. Keep It Current
+
+Skills should reflect current practices. When workflows change:
+- Update the skill document
+- Remove obsolete patterns
+- Add new best practices
+
+## Annotated Examples
+
+Let's examine the existing skills to understand effective patterns.
+
+### Example 1: gitea (Tool Reference)
+
+The `gitea` skill is a **tool reference**—it documents how to use a specific CLI tool.
+
+```markdown
+# Forgejo CLI (fj)
+
+Command-line interface for interacting with Forgejo repositories.
+
+## Authentication
+The `tea` CLI authenticates via `tea auth login`. Credentials are stored locally.
+
+## Common Commands
+
+### Issues
+\```bash
+# List issues
+tea issue search -s open              # Open issues
+tea issue search -s closed            # Closed issues
+...
+\```
+```
+
+**Key patterns:**
+- Organized by feature area (Issues, Pull Requests, Repository)
+- Includes actual command syntax with comments
+- Covers common use cases, not exhaustive documentation
+- Tips section for non-obvious behaviors
+
+### Example 2: issue-writing (Process Knowledge)
+
+The `issue-writing` skill is **process knowledge**—it teaches how to do something well.
+
+```markdown
+# Issue Writing
+
+How to write clear, actionable issues.
+
+## Issue Structure
+
+### Title
+- Start with action verb: "Add", "Fix", "Update", "Remove"
+- Be specific: "Add user authentication" not "Auth stuff"
+- Keep under 60 characters
+
+### Description
+\```markdown
+## Summary
+One paragraph explaining what and why.
+
+## Acceptance Criteria
+- [ ] Specific, testable requirement
+...
+\```
+```
+
+**Key patterns:**
+- Clear guidelines with specific rules
+- Templates for different issue types
+- Good/bad examples for each guideline
+- Covers the full lifecycle (structure, criteria, labels, dependencies)
+
+### Example 3: backlog-grooming (Workflow Checklist)
+
+The `backlog-grooming` skill is a **workflow checklist**—it provides a systematic process.
+
+```markdown
+# Backlog Grooming
+
+How to review and improve existing issues.
+
+## Grooming Checklist
+
+For each issue, verify:
+
+### 1. Title Clarity
+- [ ] Starts with action verb
+- [ ] Specific and descriptive
+- [ ] Understandable without reading description
+...
+```
+
+**Key patterns:**
+- Structured as a checklist with categories
+- Each item is a yes/no verification
+- Includes workflow steps (Grooming Workflow section)
+- Questions to guide decision-making
+
+### Example 4: roadmap-planning (Strategy Guide)
+
+The `roadmap-planning` skill is a **strategy guide**—it teaches how to think about a problem.
+
+```markdown
+# Roadmap Planning
+
+How to plan features and create issues for implementation.
+
+## Planning Process
+
+### 1. Understand the Goal
+- What capability or improvement is needed?
+- Who benefits and how?
+- What's the success criteria?
+
+### 2. Break Down the Work
+- Identify distinct components
+- Define boundaries between pieces
+...
+```
+
+**Key patterns:**
+- Process-oriented with numbered steps
+- Multiple breakdown strategies (by layer, by user story, by component)
+- Concrete examples showing the pattern applied
+- Questions to guide planning decisions
+
+## When to Create a New Skill
+
+Create a skill when you find yourself:
+
+1. **Explaining the same concepts repeatedly** across different conversations
+2. **Wanting consistent quality** in a specific area
+3. **Building up domain expertise** that should persist
+4. **Needing a reusable reference** for commands or agents
+
+### Signs You Need a New Skill
+
+- You're copy-pasting the same guidelines
+- Multiple commands need the same knowledge
+- Quality is inconsistent without explicit guidance
+- There's a clear domain that doesn't fit existing skills
+
+### Signs You Don't Need a New Skill
+
+- The knowledge is only used once
+- It's already covered by an existing skill
+- It's too generic to be actionable
+- It's better as part of a command's instructions
+
+## Skill Lifecycle
+
+### 1. Draft
+
+Start with the essential content:
+- Core patterns and templates
+- Key guidelines
+- A few examples
+
+### 2. Refine
+
+As you use the skill, improve it:
+- Add examples from real usage
+- Clarify ambiguous guidelines
+- Remove unused content
+
+### 3. Maintain
+
+Keep skills current:
+- Update when practices change
+- Remove obsolete patterns
+- Add newly discovered best practices
+
+## Checklist: Before Submitting a New Skill
+
+- [ ] File is at `skills/<name>/SKILL.md`
+- [ ] Name follows kebab-case convention
+- [ ] Skill focuses on a single domain
+- [ ] Guidelines are specific and actionable
+- [ ] Examples illustrate each major point
+- [ ] Templates are provided where appropriate
+- [ ] Common mistakes are documented
+- [ ] Skill is referenced by at least one command or agent
+
+## See Also
+
+- [ARCHITECTURE.md](../ARCHITECTURE.md): How skills fit into the overall system
+- [VISION.md](../VISION.md): The philosophy behind composable components

index.ts

@@ -1 +0,0 @@
-console.log("Hello via Bun!");

models.yaml

@@ -1,26 +0,0 @@
-manager:
-  memory_budget: 450
-  contention_policy:
-    strategy: wait_then_preempt
-    wait_timeout_s: 45
-    preempt_after_s: 15
-
-models:
-  - name: Qwen-Coder-Next
-    model: mlx-community/Qwen3-Coder-Next-4bit
-    estimated_memory_gb: 50
-    reasoning_parser: qwen3
-
-  - name: Qwen3.6
-    model: mlx-community/Qwen3.6-35B-A3B-6bit
-    estimated_memory_gb: 40
-    reasoning_parser: qwen3
-
-  - name: gemma
-    model: mlx-community/gemma-4-31b-it-8bit
-    estimated_memory_gb: 40
-    reasoning_parser: gemma4
-
-  - name: MiniMax-M3
-    model: pipenetwork/MiniMax-M3-MLX-mixed-3_6bit
-    estimated_memory_gb: 200

package.json

@@ -1,12 +0,0 @@
-{
-  "name": "architecture",
-  "module": "index.ts",
-  "type": "module",
-  "private": true,
-  "devDependencies": {
-    "@types/bun": "latest"
-  },
-  "peerDependencies": {
-    "typescript": "^5"
-  }
-}

sample_opencode.json

@@ -1,35 +0,0 @@
-{
-  "$schema": "https://opencode.ai/config.json",
-  "provider": {
-    "odin": {
-      "npm": "@ai-sdk/anthropic",
-      "name": "Odin",
-      "options": {
-        "baseURL": "http://192.168.2.49:12000/v1",
-        "apiKey": "changeme"
-      },
-      "models": {
-        "Qwen-Coder-Next": {
-          "name": "Qwen-Coder-Next",
-          "tool_call": true,
-          "options": {
-            "temperature": 1.0,
-            "top_p": 0.95
-          }
-        },
-        "Qwen3.6": {
-          "name": "Qwen3.6",
-          "tool_call": true
-        },
-        "gemma": {
-          "name": "gemma",
-          "tool_call": true
-        },
-        "MiniMax-M3": {
-          "name": "MiniMax-M3",
-          "tool_call": true
-        }
-      }
-    }
-  }
-}

scripts/pre-commit-checks.sh

@@ -0,0 +1,50 @@
+#!/bin/bash
+# Pre-commit validation script for Claude Code
+# Validates YAML, checks for secrets, validates K8s manifests
+
+set -e
+
+# Get staged files
+STAGED_FILES=$(git diff --cached --name-only 2>/dev/null || echo "")
+
+if [ -z "$STAGED_FILES" ]; then
+  exit 0
+fi
+
+# Check for potential secrets in staged files
+echo "Checking for potential secrets..."
+SECRET_PATTERN='(password|secret|token|api_key|apikey|private_key).*[=:].{20,}'
+if echo "$STAGED_FILES" | xargs grep -l -iE "$SECRET_PATTERN" 2>/dev/null | grep -v '.sops.yaml' | grep -v 'secret.*\.enc\.yaml'; then
+  echo "WARNING: Potential secrets detected in staged files (excluding SOPS-encrypted files)"
+  echo "Please verify these are encrypted or not actual secrets."
+fi
+
+# Validate YAML syntax
+echo "Validating YAML syntax..."
+for file in $(echo "$STAGED_FILES" | grep -E '\.ya?ml$'); do
+  if [ -f "$file" ]; then
+    if ! python3 -c "import yaml; yaml.safe_load(open('$file'))" 2>/dev/null; then
+      echo "ERROR: Invalid YAML syntax: $file"
+      exit 1
+    fi
+  fi
+done
+
+# Validate Kubernetes manifests (if kubectl available)
+if command -v kubectl &>/dev/null; then
+  echo "Validating Kubernetes manifests..."
+  for file in $(echo "$STAGED_FILES" | grep -E '\.ya?ml$'); do
+    if [ -f "$file" ] && grep -q "^kind:" "$file" 2>/dev/null; then
+      # Skip SOPS-encrypted files and kustomization files
+      if echo "$file" | grep -qE '(\.sops\.yaml|\.enc\.yaml|kustomization\.yaml)$'; then
+        continue
+      fi
+      if ! kubectl apply --dry-run=client -f "$file" 2>/dev/null; then
+        echo "WARNING: Kubernetes validation failed: $file (may be expected for partial manifests)"
+      fi
+    fi
+  done
+fi
+
+echo "Pre-commit checks passed."
+exit 0

settings.json

@@ -1,4 +1,5 @@
 {
+  "model": "opus",
   "permissions": {
     "allow": [
       "Bash(git:*)",
@@ -9,6 +10,13 @@
       "WebSearch"
     ]
   },
+  "statusLine": {
+    "type": "command",
+    "command": "input=$(cat); current_dir=$(echo \"$input\" | jq -r '.workspace.current_dir'); model=$(echo \"$input\" | jq -r '.model.display_name'); style=$(echo \"$input\" | jq -r '.output_style.name'); git_info=\"\"; if [ -d \"$current_dir/.git\" ]; then cd \"$current_dir\" && branch=$(git branch --show-current 2>/dev/null) && status=$(git status --porcelain 2>/dev/null | wc -l | tr -d ' ') && git_info=\" [$branch$([ \"$status\" != \"0\" ] && echo \"*\")]\"; fi; printf \"\\033[2m$(whoami)@$(hostname -s) $(basename \"$current_dir\")$git_info | $model ($style)\\033[0m\""
+  },
+  "enabledPlugins": {
+    "gopls-lsp@claude-plugins-official": true
+  },
   "hooks": {
     "PreToolUse": [
       {
@@ -22,14 +30,5 @@
         ]
       }
     ]
-  },
+  }
-  "statusLine": {
-    "type": "command",
-    "command": "input=$(cat); current_dir=$(echo \"$input\" | jq -r '.workspace.current_dir'); model=$(echo \"$input\" | jq -r '.model.display_name'); style=$(echo \"$input\" | jq -r '.output_style.name'); git_info=\"\"; if [ -d \"$current_dir/.git\" ]; then cd \"$current_dir\" && branch=$(git branch --show-current 2>/dev/null) && status=$(git status --porcelain 2>/dev/null | wc -l | tr -d ' ') && git_info=\" [$branch$([ \"$status\" != \"0\" ] && echo \"*\")]\"; fi; printf \"\\033[2m$(whoami)@$(hostname -s) $(basename \"$current_dir\")$git_info | $model ($style)\\033[0m\"",
-    "padding": 0
-  },
-  "enabledPlugins": {
-    "gopls-lsp@claude-plugins-official": true
-  },
-  "model": "opus"
 }

skills/backlog-grooming/SKILL.md

@@ -0,0 +1,90 @@
+---
+name: backlog-grooming
+description: How to review and improve existing issues for clarity and actionability
+---
+
+# Backlog Grooming
+
+How to review and improve existing issues.
+
+## Grooming Checklist
+
+For each issue, verify:
+
+### 1. Title Clarity
+- [ ] Starts with action verb
+- [ ] Specific and descriptive
+- [ ] Understandable without reading description
+
+### 2. Description Quality
+- [ ] Has clear summary
+- [ ] Explains the "why"
+- [ ] Provides enough context
+
+### 3. Acceptance Criteria
+- [ ] Criteria exist
+- [ ] Each criterion is testable
+- [ ] Criteria are specific (not vague)
+- [ ] Complete set (nothing missing)
+
+### 4. Scope
+- [ ] Not too broad (can complete in reasonable time)
+- [ ] Not too narrow (meaningful unit of work)
+- [ ] Clear boundaries (what's included/excluded)
+
+### 5. Dependencies
+- [ ] Dependencies identified
+- [ ] No circular dependencies
+- [ ] Blocking issues are tracked
+
+### 6. Labels
+- [ ] Type label (bug/feature/etc)
+- [ ] Priority if applicable
+- [ ] Component labels if applicable
+
+## Common Issues to Fix
+
+### Vague Titles
+- Bad: "Fix bug"
+- Good: "Fix login form validation on empty email"
+
+### Missing Acceptance Criteria
+Add specific, testable criteria based on the description.
+
+### Scope Creep
+If issue covers multiple features, split into separate issues.
+
+### Stale Issues
+- Close if no longer relevant
+- Update if context has changed
+- Add "needs-triage" label if unclear
+
+### Duplicate Issues
+- Close duplicate with reference to original
+- Merge relevant details into original
+
+## Grooming Workflow
+
+Use the gitea skill for issue operations.
+
+1. **Fetch open issues**
+2. **Review each issue** against checklist
+3. **Improve or flag** issues that need work
+4. **Update issue** with improvements
+5. **Add labels** as needed
+
+## Questions to Ask
+
+When grooming, consider:
+- "Could a developer start work on this today?"
+- "How will we know when this is done?"
+- "Is the scope clear?"
+- "Are dependencies explicit?"
+
+## Batch Grooming
+
+When grooming multiple issues:
+1. List all open issues
+2. Categorize by quality (ready, needs-work, stale)
+3. Focus on "needs-work" issues
+4. Present summary of changes made

skills/code-review/SKILL.md

@@ -0,0 +1,204 @@
+---
+name: code-review
+description: Guidelines and templates for reviewing code changes in pull requests
+---
+
+# Code Review
+
+Guidelines for reviewing code changes in pull requests.
+
+## Review Categories
+
+### Code Quality
+
+Look for:
+- **Readability**: Clear naming, logical structure, appropriate comments
+- **Maintainability**: Easy to modify, follows DRY, single responsibility
+- **Complexity**: Avoid deep nesting, overly long functions, complex conditionals
+- **Dead code**: Unused variables, unreachable code, commented-out blocks
+
+Questions to ask:
+- Can someone unfamiliar with this code understand it quickly?
+- Would I be comfortable maintaining this code?
+- Does this follow existing patterns in the codebase?
+
+### Potential Bugs
+
+Look for:
+- **Edge cases**: Empty arrays, null values, boundary conditions
+- **Logic errors**: Off-by-one, incorrect operators, inverted conditions
+- **Race conditions**: Async operations, shared state
+- **Resource leaks**: Unclosed connections, missing cleanup
+- **Error handling**: Unhandled exceptions, silent failures
+
+Questions to ask:
+- What happens with unexpected input?
+- Are all error paths handled appropriately?
+- Could concurrent execution cause issues?
+
+### Security Concerns
+
+Look for:
+- **Injection**: SQL, command, XSS vulnerabilities
+- **Authentication**: Bypasses, weak validation
+- **Authorization**: Missing permission checks
+- **Data exposure**: Logging secrets, exposing internals
+- **Dependencies**: Known vulnerabilities in imports
+
+Questions to ask:
+- Could an attacker exploit this?
+- Is user input properly validated and sanitized?
+- Are secrets properly protected?
+
+### Style & Consistency
+
+Look for:
+- **Naming conventions**: Match existing codebase style
+- **Formatting**: Consistent indentation, spacing
+- **File organization**: Logical grouping, appropriate location
+- **Import order**: Following project conventions
+
+Note: Style issues are lower priority than functional concerns.
+
+### Test Coverage
+
+Look for:
+- **Missing tests**: New functionality without tests
+- **Edge cases**: Boundary conditions not tested
+- **Error paths**: Exception handling not verified
+- **Integration**: Component interactions not covered
+
+Questions to ask:
+- Would these tests catch a regression?
+- Are the assertions meaningful?
+- Do tests cover the acceptance criteria?
+
+## Review Process
+
+1. **Understand context**: Read PR description and linked issues
+2. **High-level scan**: Understand overall structure and approach
+3. **Detailed review**: Go through changes file by file
+4. **Consider impact**: Think about side effects and dependencies
+5. **Provide feedback**: Be constructive and specific
+
+## Writing Review Comments
+
+### Be Constructive
+- Explain *why* something is an issue
+- Suggest alternatives when possible
+- Distinguish between blocking issues and suggestions
+
+### Be Specific
+- Reference exact lines or code blocks
+- Provide concrete examples
+- Link to relevant documentation or patterns
+
+### Be Kind
+- Phrase feedback as questions when appropriate
+- Acknowledge good solutions
+- Remember there's a person receiving this feedback
+
+## Example Review Comments
+
+### Code Quality
+
+**Good:**
+> `src/utils/parser.ts:45` - This function is doing three things: parsing, validating, and transforming. Consider splitting into `parse()`, `validate()`, and `transform()` to improve testability and make each responsibility clear.
+
+**Bad:**
+> This code is messy, please clean it up.
+
+### Potential Bugs
+
+**Good:**
+> `src/api/users.ts:23` - `users.find()` returns `undefined` when no match is found, but line 25 accesses `user.id` without a null check. This will throw when the user doesn't exist. Consider: `const user = users.find(...); if (!user) return null;`
+
+**Bad:**
+> This might crash.
+
+### Security
+
+**Good:**
+> `src/routes/search.ts:12` - The query parameter is interpolated directly into the SQL string, which allows SQL injection. Use parameterized queries instead: `db.query('SELECT * FROM items WHERE name = ?', [query])`
+
+**Bad:**
+> Security issue here.
+
+### Style
+
+**Good:**
+> `src/components/Button.tsx:8` - Minor: The codebase uses `camelCase` for event handlers (e.g., `handleClick`), but this uses `on_click`. Consider renaming for consistency.
+
+**Bad:**
+> Wrong naming convention.
+
+### Test Coverage
+
+**Good:**
+> The happy path is well tested. Consider adding a test for when `fetchUser()` rejects - the error handling in line 34 isn't currently covered.
+
+**Bad:**
+> Need more tests.
+
+### Positive Feedback
+
+**Good:**
+> Nice use of the builder pattern here - it makes the configuration much more readable than the previous approach with multiple boolean flags.
+
+## Verdict Criteria
+
+### LGTM (Looks Good To Me)
+- No blocking issues
+- Code meets quality standards
+- Tests are adequate
+- Ready to merge
+
+### Needs Changes
+- Minor issues that should be addressed
+- Style improvements
+- Missing tests for edge cases
+- Not blocking, but worth fixing
+
+### Blocking Issues
+- Security vulnerabilities
+- Logic errors that would cause bugs
+- Missing critical functionality
+- Breaking changes without migration
+
+## Review Comment Template
+
+```markdown
+## AI Code Review
+
+> This is an automated review generated by the code-reviewer agent.
+
+### Summary
+[1-2 sentence overall assessment of the changes]
+
+### Findings
+
+#### Code Quality
+- [Issue with specific file:line reference and explanation]
+- [Or "Code is well-structured and readable"]
+
+#### Potential Bugs
+- [Bug risk with explanation]
+- [Or "No obvious issues found"]
+
+#### Security Concerns
+- [Security issue with severity]
+- [Or "No security concerns identified"]
+
+#### Style Notes
+- [Style improvement suggestion]
+- [Or "Consistent with codebase conventions"]
+
+#### Test Coverage
+- [Missing test scenario]
+- [Or "Tests adequately cover changes"]
+
+### Verdict
+**[LGTM / Needs Changes / Blocking Issues]**
+
+[Brief explanation of verdict]
+```

skills/gitea/SKILL.md

@@ -0,0 +1,188 @@
+---
+name: gitea
+description: Gitea CLI (tea) for issues, pull requests, and repository management
+---
+
+# Gitea CLI (tea)
+
+Command-line interface for interacting with Gitea repositories.
+
+## Installation
+
+```bash
+brew install tea
+```
+
+## Authentication
+
+The `tea` CLI authenticates via `tea logins add`. Credentials are stored locally by tea.
+
+```bash
+tea logins add                       # Interactive login
+tea logins add --url <url> --token <token> --name <name>  # Non-interactive
+tea logins list                      # Show configured logins
+tea logins default <name>            # Set default login
+```
+
+## Configuration
+
+Config is stored at `~/Library/Application Support/tea/config.yml` (macOS).
+
+To avoid needing `--login` on every command, set defaults:
+
+```yaml
+preferences:
+    editor: false
+    flag_defaults:
+        remote: origin
+        login: git.flowmade.one
+```
+
+## Repository Detection
+
+`tea` automatically detects the repository from git remotes when run inside a git repository. Use `--remote <name>` to specify which remote to use.
+
+## Common Commands
+
+### Issues
+
+```bash
+# List issues
+tea issues                           # Open issues (default)
+tea issues --state all               # All issues
+tea issues --state closed            # Closed issues
+
+# View issue details
+tea issues <number>                  # Full issue details
+tea issues <number> --comments       # Include comments
+
+# Create issue
+tea issues create --title "<title>" --description "<body>"
+tea issues create -t "<title>" -d "<body>"
+
+# Edit issue
+tea issues edit <number> --title "<new-title>"
+tea issues edit <number> --description "<new-body>"
+
+# Close/reopen
+tea issues close <number>
+tea issues reopen <number>
+
+# Labels
+tea issues edit <number> --labels "bug,help wanted"
+```
+
+### Pull Requests
+
+```bash
+# List PRs
+tea pulls                            # Open PRs (default)
+tea pulls --state all                # All PRs
+tea pulls --state closed             # Closed/merged PRs
+
+# View PR
+tea pulls <number>                   # PR details
+tea pulls <number> --comments        # Include comments
+tea pulls <number> -f diff           # PR diff
+
+# Create PR
+tea pulls create --title "<title>" --description "<body>"
+tea pulls create -t "<title>" -d "<body>"
+tea pulls create -t "<title>" -d "Closes #<issue>"
+tea pulls create --head <branch> --base main -t "<title>"
+
+# Checkout PR locally
+tea pulls checkout <number>
+
+# Review/Approve
+tea pulls approve <number>           # Approve PR (LGTM)
+tea pulls reject <number>            # Request changes
+tea pulls review <number>            # Interactive review
+
+# Merge
+tea pulls merge <number>                      # Default merge
+tea pulls merge <number> --style squash       # Squash commits
+tea pulls merge <number> --style rebase       # Rebase commits
+tea pulls merge <number> --style rebase-merge # Rebase then merge
+
+# Clean up after merge
+tea pulls clean <number>             # Delete local & remote branch
+```
+
+### Repository
+
+```bash
+tea repos                            # List repos
+tea repos <owner>/<repo>             # Repository info
+tea clone <owner>/<repo>             # Clone repository
+```
+
+### Comments
+
+```bash
+# Add comment to issue or PR
+tea comment <number> "<comment body>"
+tea comment 3 "LGTM, ready to merge"
+
+# Multiline comments (use quoted strings with literal newlines)
+tea comment 3 "## Review Summary
+
+- Code looks good
+- Tests pass"
+```
+
+> **Warning**: Do not use heredoc syntax `$(cat <<'EOF'...EOF)` with `tea comment` - it causes the command to be backgrounded and fail silently.
+
+### Notifications
+
+```bash
+tea notifications                    # List notifications
+tea notifications --mine             # Only participating
+```
+
+## Output Formatting
+
+Most commands support `--output` or `-o` flag:
+- `-o simple` - Plain text
+- `-o table` - Tabular format (default)
+- `-o json` - Machine-readable JSON
+- `-o yaml` - YAML format
+- `-o csv` - CSV format
+
+## Specifying Remote/Login
+
+```bash
+tea issues --remote gitea            # Use specific git remote
+tea issues --login myserver          # Use specific login
+tea issues -r owner/repo             # Specify repo directly
+```
+
+## Tips
+
+- **View single issue**: Use `tea issues <number>` (NOT `tea issues view <number>` - there is no `view` subcommand)
+- **PR description flag**: Use `--description` or `-d` (NOT `--body` like gh CLI)
+- Always verify you're in the correct repository before running commands
+- Use `tea issues` to find issue numbers before viewing/editing
+- Reference issues in PR bodies with `Closes #N` for auto-linking
+- Use `--remote gitea` when you have multiple remotes (e.g., origin + gitea)
+- The `tea pulls checkout` command is handy for reviewing PRs locally
+
+## Actions / CI
+
+```bash
+# List workflow runs
+tea actions runs                     # List all workflow runs
+tea actions runs -o json             # JSON output for parsing
+
+# List jobs for a run
+tea actions jobs <run-id>            # Show jobs for a specific run
+tea actions jobs <run-id> -o json    # JSON output
+
+# Get job logs
+tea actions logs <job-id>            # Display logs for a job
+
+# Full workflow: find failed job logs
+tea actions runs                     # Find the run ID
+tea actions jobs <run-id>            # Find the job ID
+tea actions logs <job-id>            # View the logs
+```

skills/issue-writing/SKILL.md

@@ -0,0 +1,110 @@
+---
+name: issue-writing
+description: How to write clear, actionable issues with proper structure and acceptance criteria
+---
+
+# Issue Writing
+
+How to write clear, actionable issues.
+
+## Issue Structure
+
+### Title
+- Start with action verb: "Add", "Fix", "Update", "Remove", "Refactor"
+- Be specific: "Add user authentication" not "Auth stuff"
+- Keep under 60 characters when possible
+
+### Description
+
+```markdown
+## Summary
+One paragraph explaining what and why.
+
+## Acceptance Criteria
+- [ ] Specific, testable requirement
+- [ ] Another requirement
+- [ ] User can verify this works
+
+## Context
+Additional background, links, or references.
+
+## Technical Notes (optional)
+Implementation hints or constraints.
+```
+
+## Writing Acceptance Criteria
+
+Good criteria are:
+- **Specific**: "User sees error message" not "Handle errors"
+- **Testable**: Can verify pass/fail
+- **User-focused**: What the user experiences
+- **Independent**: Each stands alone
+
+Examples:
+```markdown
+- [ ] Login form validates email format before submission
+- [ ] Invalid credentials show "Invalid email or password" message
+- [ ] Successful login redirects to dashboard
+- [ ] Session persists across browser refresh
+```
+
+## Issue Types
+
+### Bug Report
+```markdown
+## Summary
+Description of the bug.
+
+## Steps to Reproduce
+1. Go to...
+2. Click...
+3. Observe...
+
+## Expected Behavior
+What should happen.
+
+## Actual Behavior
+What happens instead.
+
+## Environment
+- Browser/OS/Version
+```
+
+### Feature Request
+```markdown
+## Summary
+What feature and why it's valuable.
+
+## Acceptance Criteria
+- [ ] ...
+
+## User Story (optional)
+As a [role], I want [capability] so that [benefit].
+```
+
+### Technical Task
+```markdown
+## Summary
+What technical work needs to be done.
+
+## Scope
+- Include: ...
+- Exclude: ...
+
+## Acceptance Criteria
+- [ ] ...
+```
+
+## Labels
+
+Use labels to categorize:
+- `bug`, `feature`, `enhancement`, `refactor`
+- `priority/high`, `priority/low`
+- Component labels specific to project
+
+## Dependencies
+
+Reference related issues:
+- "Depends on #N" - Must complete first
+- "Blocks #N" - This blocks another
+- "Related to #N" - Informational link

skills/roadmap-planning/SKILL.md

@@ -0,0 +1,113 @@
+---
+name: roadmap-planning
+description: How to plan features and create issues for implementation
+---
+
+# Roadmap Planning
+
+How to plan features and create issues for implementation.
+
+## Planning Process
+
+### 1. Understand the Goal
+- What capability or improvement is needed?
+- Who benefits and how?
+- What's the success criteria?
+
+### 2. Break Down the Work
+- Identify distinct components
+- Define boundaries between pieces
+- Aim for issues that are:
+  - Completable in 1-3 focused sessions
+  - Independently testable
+  - Clear in scope
+
+### 3. Identify Dependencies
+- Which pieces must come first?
+- What can be parallelized?
+- Are there external blockers?
+
+### 4. Create Issues
+- Follow issue-writing patterns
+- Reference dependencies explicitly
+- Use consistent labeling
+
+## Breaking Down Features
+
+### By Layer
+```
+Feature: User Authentication
+├── Data layer: User model, password hashing
+├── API layer: Login/logout endpoints
+├── UI layer: Login form, session display
+└── Integration: Connect all layers
+```
+
+### By User Story
+```
+Feature: Shopping Cart
+├── Add item to cart
+├── View cart contents
+├── Update quantities
+├── Remove items
+└── Proceed to checkout
+```
+
+### By Technical Component
+```
+Feature: Real-time Updates
+├── WebSocket server setup
+├── Client connection handling
+├── Message protocol
+├── Reconnection logic
+└── Integration tests
+```
+
+## Issue Ordering
+
+### Dependency Chain
+Create issues in implementation order:
+1. Foundation (models, types, interfaces)
+2. Core logic (business rules)
+3. Integration (connecting pieces)
+4. Polish (error handling, edge cases)
+
+### Reference Pattern
+In issue descriptions:
+```markdown
+## Dependencies
+- Depends on #12 (user model)
+- Depends on #13 (API setup)
+```
+
+## Creating Issues
+
+Use the gitea skill for issue operations.
+
+### Single Issue
+Create with a descriptive title and structured body:
+- Summary section
+- Acceptance criteria (testable checkboxes)
+- Dependencies section referencing blocking issues
+
+### Batch Creation
+When creating multiple related issues:
+1. Plan all issues first
+2. Create in dependency order
+3. Update earlier issues with forward references
+
+## Roadmap View
+
+To see current roadmap:
+1. List open issues using the gitea skill
+2. Group by labels/milestones
+3. Identify blocked vs ready issues
+4. Prioritize based on dependencies and value
+
+## Planning Questions
+
+Before creating issues, answer:
+- "What's the minimum viable version?"
+- "What can we defer?"
+- "What are the riskiest parts?"
+- "How will we validate each piece?"

tsconfig.json

@@ -1,29 +0,0 @@
-{
-  "compilerOptions": {
-    // Environment setup & latest features
-    "lib": ["ESNext"],
-    "target": "ESNext",
-    "module": "Preserve",
-    "moduleDetection": "force",
-    "jsx": "react-jsx",
-    "allowJs": true,
-
-    // Bundler mode
-    "moduleResolution": "bundler",
-    "allowImportingTsExtensions": true,
-    "verbatimModuleSyntax": true,
-    "noEmit": true,
-
-    // Best practices
-    "strict": true,
-    "skipLibCheck": true,
-    "noFallthroughCasesInSwitch": true,
-    "noUncheckedIndexedAccess": true,
-    "noImplicitOverride": true,
-
-    // Some stricter flags (disabled by default)
-    "noUnusedLocals": false,
-    "noUnusedParameters": false,
-    "noPropertyAccessFromIndexSignature": false
-  }
-}