Claude Code Toolkit

⚠️ This repo has been superseded.
The single-agent, Claude-Code-only patterns here have been rewritten as
coding-agent-toolkit —
a cross-agent workflow layer that runs on both Claude Code and OpenAI Codex,
with the same skills accessible as slash commands on either host.
The successor covers:
- align → plan → plan-issues → next-issue → ship — an explicit
  spec-first workflow with GitHub milestones + issues as the durable plan trail.
- handoff / continue — cold-startable session transitions written to disk,
  so either agent can resume any prior session.
- Optional continuous review via roborev.
This repo remains available for reference but will not receive further updates.
New work should target the successor.

Claude Code Toolkit

Production-tested commands, skills, and patterns for Claude Code

Overview

A collection of plugins, skills, and patterns developed through 6+ months of daily Claude Code use. Copy what works, adapt to your needs.

What's included: 28 commands, 5 agents, and 6 domain skills across 6 core plugins.

Design Goals

1. Stateless architecture - Commands execute independently, state persisted in files
2. File-based persistence - JSON and Markdown for all state management
3. MCP integration - Optional Model Context Protocol tools with graceful degradation
4. Progressive disclosure - Load context incrementally to optimize token usage
5. Self-containment - All logic inline, no external script dependencies

Key Capabilities

- Workflow management: explore → plan → next → ship pattern
- Memory persistence: Cross-session context with automatic reflection
- Quality automation: Git safety, pre/post hooks, compliance auditing
- MCP integration: Optional tools (Serena, Sequential Thinking) with graceful degradation
- Domain adaptation: Examples showing how…