Verify repository state and perform explicitly authorized Git and publication actions: commit, push, pull request, tag, release, or deploy. Runs only on an explicit CoderKit commit request.
Reproduce unexpected behavior, trace the real path, and isolate the root cause before an authorized fix. Runs only on an explicit CoderKit debug request.
Understand the code and the solution space: trace real flows, compare genuinely different approaches, and choose a direction. Runs only on an explicit CoderKit explore request.
Implement an approved request or plan using project conventions and proportionate verification. Runs only on an explicit CoderKit implement request.
Inspect the actual project and create an actionable, evidence-grounded implementation plan without editing implementation files. Runs only on an explicit CoderKit plan request.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
CoderKit is an optional engineering toolbox for coding agents. Workflows run only when explicitly requested and are never started automatically. Each tool finishes by naming the natural next step for the user to invoke — a suggestion only, never an automatic handoff, and never offered outside an explicitly requested workflow.
| Tool | Purpose |
|---|---|
explore | Understand the code and choose a direction — read-only. |
plan | Turn the direction into an implementation plan. |
implement | Implement with proportionate verification. |
debug | Reproduce and isolate a root cause. |
verify | Run real checks and review the change for correctness and risk. |
commit | Perform explicitly authorized Git and publication actions. |
The common path is explore → plan → implement → verify → commit, with debug available when needed. It is not mandatory: every tool works independently, and the user drives the sequencing.
Work products persist in the target project under docs/work/NNN-short-name/: plan writes plan.md, and implement maintains tasks.md (main tasks, subtasks, and subagent assignments) as the build loop progresses. Exploration stays conversational and leaves no artifact.
codex plugin marketplace add sbusso/coderkit --ref v0.6.0
codex plugin add coderkit@coderkit
Invoke a workflow in plain language, for example: Use CoderKit to explore this feature.
claude plugin marketplace add sbusso/[email protected] --scope user
claude plugin install coderkit@coderkit --scope user
Invoke a workflow with /coderkit:explore, /coderkit:plan, /coderkit:implement, /coderkit:debug, /coderkit:verify, or /coderkit:commit.
bun run check
claude plugin validate packages/claude-code --strict
uv run --with pyyaml -- python3 ~/.codex/skills/.system/plugin-creator/scripts/validate_plugin.py packages/codex
Canonical workflows live in core/; bun run build generates both native packages. Generated files are committed for direct installation.
CoderKit contains no hooks, telemetry, background services, MCP servers, remote branding, or automatic publication behavior.
CoderKit is an independent MIT-licensed project inspired by Superpowers, Compound Engineering, and OpenAI's outcome-first prompting guidance.
npx claudepluginhub sbusso/coderkit --plugin coderkitPersistent agent orchestrator for Claude Code. Multi-channel message routing, triage, and SWE task management. Run /claudeclaw:setup to create your first instance and configure channels.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques