By anutron
Spec-driven development workflow for Claude Code that enforces OpenSpec change planning, TDD, worktree-isolated agent execution, structured review, and PR automation across the entire commit-to-release cycle.
Use when executing implementation plans with independent tasks — orchestration pattern for worktree isolation, TDD discipline, and two-stage review. Referenced by execute-plan, fixit, and bugbash.
Install the anutron (claude-skills) kit into the current project — symlinks or copies skills, registers hooks, compiles CLAUDE.md from snippets.
Uninstall the anutron (claude-skills) kit from the current project — reverses everything /anutron-install did.
Reference for bash patterns that trigger Claude Code permission guardrails (static-analysis flags that allowlist rules cannot silence). Load when about to run bash with `cd <repo> && git ...`, `$(...)`, backticks, heredocs, inline `python3 -c` / `node -e` / `ruby -e` / `perl -e`, multi-line shell logic with variables/conditionals, or before allowlisting a new script path. Also covers always-prompt verbs and the `git -C` known gap.
You MUST use this before any creative work -- creating features, building components, adding functionality, or modifying behavior. Explores intent, designs the solution, scaffolds an OpenSpec change folder (proposal + design + delta specs + tasks), and hands off to execution.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Two things in one repo:
Steal what's useful. Most people point Claude at this repo and cherry-pick what fits their workflow.
📘 Rolling out Claude Code at your organization? See the adoption recipes – opinionated patterns for project organization, design-to-execution workflow, AI security, and data proxies. Each recipe pairs an approachable description for non-technical readers with a technical reference for Claude.
The fastest path: install as a plugin and run the setup wizard.
/plugin install claude-skills@anutron/claude-skills
/claude-skills:setup
That gets you everything – skills, rules, hooks, status line – with interactive setup and auto-updates.
Three other paths exist: per-project sandbox (no global install), clone-and-promote (full control), and steal-the-pieces (cherry-pick). See the quick start guide for all four.
Six docs cover how the pieces fit together.

How the skills compose into a single development cycle. The skill cascade (brainstorm, execute-plan, ralph-review, spec-audit, bugbash, fixit), what each step produces, how it hands off to the next, and the WHY of specs as the source of truth.

The OpenSpec-based workflow: idea → spec → plan → test → implement → review. The full skill set, setup instructions, and how it degrades gracefully when not all pieces are present.
Read about spec-driven development →

The complete index of skills, grouped by purpose – development, discipline and orchestration, git/PR, and general utilities.

Version-controlled CLAUDE.md snippets with a compilation system. Each rule is a small focused snippet that compiles into the final CLAUDE.md – portable, reviewable, and template-variable-aware.

The set-topic skill plus the hook that ensures Claude actually uses it. Displays in the status line for easy session identification.
![]()
Three hooks that track which skills get invoked and which get loaded as dependencies. Pair with /skill-audit for periodic pruning recommendations.
Read about skill usage tracking →
A set of opinionated patterns for orgs scaling Claude Code adoption – covers personal workshops, the design-to-execution pipeline, AI security, and data proxies. Each recipe has an approachable orientation up top and a technical reference at the bottom for Claude.
See docs/claude-code-recipes/.
| File | Description |
|---|---|
| docs/permissions-guide.md | Recommended permission rules – reduce nagging, protect sensitive files, block destructive commands |
| docs/stack-spectrum.md | Tech stack tiers from lightweight to deployable – picking the right size for the job |
| docs/handling-api-keys.md | Best practice for API keys – keep them in a vault (1Password or macOS Keychain), never on disk or in git. Covers the op-secret.md 1Password loader (bin/op-secret.sh) |
| bin/statusline.sh | Custom Claude Code status line – git status, session topic, terminal title |
| Plugin | Source | What it does |
|---|---|---|
| pr-review-toolkit | claude-plugins-official | Comprehensive PR review using specialized agents |
| commit-commands | claude-plugins-official | Git workflow shortcuts – commit, push, PR creation |
| github | claude-plugins-official | GitHub MCP integration – issues, PRs, code search |
npx claudepluginhub anutron/aiComprehensive 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.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.