# Claude Code Kit

> Drop-in starter templates that make Claude Code behave like a disciplined staff engineer instead of an eager intern. The kit is a configuration system that layers on top of Claude Code CLI: advisory rules in CLAUDE.md, deterministic shell hooks in .claude/hooks/, knowledge accumulation in tasks/lessons.md and .claude/skills/, and a project overlay (CLAUDE.project.md) that survives kit upgrades.

## Install

```bash
npx @tansuasici/claude-code-kit init
```

Source: https://claudecodekit.tansuasici.com
Repository: https://github.com/tansuasici/claude-code-kit

## Getting Started

- [Introduction](https://claudecodekit.tansuasici.com/docs): Drop-in starter templates that make Claude Code behave like a disciplined staff engineer.
- [Why This Kit](https://claudecodekit.tansuasici.com/docs/why-this-kit): How Claude Code Kit compares to .cursorrules, raw Claude Code, AGENTS.md alone, and Aider config — and when to pick which.
- [FAQ](https://claudecodekit.tansuasici.com/docs/faq): Common questions about Claude Code Kit — installation, conflicts, multi-project use, customization boundaries.
- [CLAUDE.md](https://claudecodekit.tansuasici.com/docs/claude-md): Core agent instructions — the brain of the kit.
- [Codebase Map](https://claudecodekit.tansuasici.com/docs/codebase-map): Project structure, architecture, and data flow.

## Recipes

- [Recipes](https://claudecodekit.tansuasici.com/docs/recipes): Task-specific how-to guides for common Claude Code Kit workflows.
- [Add a Project-Specific Skill](https://claudecodekit.tansuasici.com/docs/recipes/add-project-skill): Create a custom /skill-name that lives in your project, complementing the kit's built-in audit and workflow skills.
- [Enable Opt-In Hooks](https://claudecodekit.tansuasici.com/docs/recipes/enable-opt-in-hooks): Turn on auto-format, auto-lint, skill-compliance, and skill-extract-reminder — hooks the kit ships disabled by default.
- [Customize CLAUDE.project.md](https://claudecodekit.tansuasici.com/docs/recipes/customize-claude-project-md): Add stack-specific rules that override kit defaults and survive --upgrade. The project overlay is where your team's idiosyncrasies live.
- [Validate Skills in CI](https://claudecodekit.tansuasici.com/docs/recipes/validate-skills-in-ci): Run validate-skills.sh and doctor.sh on every PR via GitHub Actions, so a broken skill never lands on main.
- [Migrate from Cursor Rules](https://claudecodekit.tansuasici.com/docs/recipes/migrate-from-cursor-rules): Coming from .cursorrules? Here's how to port your conventions to Claude Code Kit's CLAUDE.md / project overlay / agent_docs structure.
- [Multi-Project Setup](https://claudecodekit.tansuasici.com/docs/recipes/multi-project-setup): Use the kit across multiple repos: per-project overlays, shared lessons, coordinated upgrades, and when to extract user-level rules.

## Workflow & Conventions

- [Workflow & Planning](https://claudecodekit.tansuasici.com/docs/workflow)
- [Conventions](https://claudecodekit.tansuasici.com/docs/conventions): These are sensible defaults. Override them in `CLAUDE.project.md` if your team has different standards.
- [Debugging](https://claudecodekit.tansuasici.com/docs/debugging)
- [Testing](https://claudecodekit.tansuasici.com/docs/testing)

## System Internals

- [Hooks](https://claudecodekit.tansuasici.com/docs/hooks): Hooks are shell scripts that run automatically at specific points in Claude Code's workflow. Unlike CLAUDE.md instructions (which are advisory), hooks are **deterministic** — they always execute.
- [Subagents](https://claudecodekit.tansuasici.com/docs/subagents)
- [Contracts](https://claudecodekit.tansuasici.com/docs/contracts)
- [Skills](https://claudecodekit.tansuasici.com/docs/skills)
- [Prompting](https://claudecodekit.tansuasici.com/docs/prompting)
- [Architecture Language](https://claudecodekit.tansuasici.com/docs/architecture-language): Shared vocabulary for /deepening-review and /interface-design — Module, Interface, Depth, Seam, Adapter, Leverage, Locality.

## Agents

- [Code Reviewer Agent](https://claudecodekit.tansuasici.com/docs/agents/code-reviewer): Thorough code reviewer focused on correctness, maintainability, and performance.
- [Security Reviewer Agent](https://claudecodekit.tansuasici.com/docs/agents/security-reviewer): Security-focused code reviewer that finds vulnerabilities.
- [Planner Agent](https://claudecodekit.tansuasici.com/docs/agents/planner): Implementation planner that analyzes tasks and produces actionable plans.
- [QA Reviewer Agent](https://claudecodekit.tansuasici.com/docs/agents/qa-reviewer): Evidence-based QA reviewer that verifies task completion.
- [Dead Code Remover Agent](https://claudecodekit.tansuasici.com/docs/agents/dead-code-remover): Removes verified unused code through static reference analysis.
- [Wiki Maintainer Agent](https://claudecodekit.tansuasici.com/docs/agents/wiki-maintainer): Knowledge wiki maintenance agent for ingest, cross-referencing, and health checks.

## Audit Skills

- [Code Quality Audit](https://claudecodekit.tansuasici.com/docs/code-quality-audit): Audits codebase for code smells, error handling gaps, and maintainability issues with actionable fix recommendations.
- [Architecture Review](https://claudecodekit.tansuasici.com/docs/architecture-review): Reviews codebase architecture for SOLID violations, dependency health, module boundaries, and structural issues.
- [Deepening Review](https://claudecodekit.tansuasici.com/docs/deepening-review): Surface shallow modules as deepening candidates, then grill the chosen one interactively — depth/seam paradigm. Use fo.
- [Interface Design](https://claudecodekit.tansuasici.com/docs/interface-design): Design It Twice — spawn 3-4 parallel sub-agents producing radically different interfaces for a module, then compare on.
- [Refactoring Guide](https://claudecodekit.tansuasici.com/docs/refactoring-guide): Provides Fowler-based refactoring recommendations with specific techniques, risk assessment, and step-by-step execution .
- [Testing Audit](https://claudecodekit.tansuasici.com/docs/testing-audit): Audits test suite for coverage gaps, test quality, flaky tests, and testing strategy alignment.
- [Dead Code Audit](https://claudecodekit.tansuasici.com/docs/dead-code-audit): Detects unused code including unreferenced functions, dead imports, orphan files, and unreachable branches.
- [Performance Audit](https://claudecodekit.tansuasici.com/docs/performance-audit): Identifies performance bottlenecks including rendering, startup, memory, and I/O issues across any tech stack.
- [Accessibility Audit](https://claudecodekit.tansuasici.com/docs/accessibility-audit): Audits UI code for WCAG 2.1 AA compliance including semantics, keyboard navigation, color contrast, and ARIA usage.
- [Dependency Audit](https://claudecodekit.tansuasici.com/docs/dependency-audit): Audits project dependencies for security vulnerabilities, outdated versions, license risks, and bloat.
- [Documentation Audit](https://claudecodekit.tansuasici.com/docs/documentation-audit): Audits code documentation quality including inline comments, API docs, README completeness, and doc-code sync.
- [Design Review](https://claudecodekit.tansuasici.com/docs/design-review): Reviews UI implementation for design consistency, visual quality, AI slop detection, and responsive behavior.
- [Project Health Report](https://claudecodekit.tansuasici.com/docs/project-health-report): Generates a comprehensive project health report covering code quality, architecture, testing, dependencies, and document.

## Workflow Skills

- [Debug](https://claudecodekit.tansuasici.com/docs/debug): Systematic root-cause debugging with evidence-before-fix enforcement and regression test generation.
- [Office Hours](https://claudecodekit.tansuasici.com/docs/office-hours): Pre-coding product validation using forcing functions — clarify what to build and why before writing any code.
- [Ship](https://claudecodekit.tansuasici.com/docs/ship): Full deployment pipeline — tests, coverage audit, CHANGELOG generation, bisectable commits, and PR creation.
- [Shape Spec](https://claudecodekit.tansuasici.com/docs/shape-spec): Creates a timestamped feature spec folder with structured plan, decisions, and references for multi-session features.
- [Retro](https://claudecodekit.tansuasici.com/docs/retro): Weekly retrospective with session analytics, LOC metrics, pattern detection, and persistent history.

## Meta Skills

- [Skill Extractor](https://claudecodekit.tansuasici.com/docs/skill-extractor): Extracts non-obvious knowledge discovered during sessions into reusable skills.
- [Skill Generator](https://claudecodekit.tansuasici.com/docs/skill-generator): Generates project-specific coding skills by analyzing tech stack and constraints.

## Wiki Module (optional, --wiki flag)

- [Wiki Schema (WIKI.md)](https://claudecodekit.tansuasici.com/docs/wiki-schema): Knowledge wiki schema — vault structure, page conventions, and operation workflows.
- [Wiki Ingest](https://claudecodekit.tansuasici.com/docs/wiki-ingest): Ingest sources into the knowledge wiki — summarize, cross-reference, and update index.
- [Wiki Lint](https://claudecodekit.tansuasici.com/docs/wiki-lint): Health-check the knowledge wiki — find contradictions, orphans, and stale content.
- [Wiki Briefing](https://claudecodekit.tansuasici.com/docs/wiki-briefing): Morning briefing from the knowledge wiki — recent activity, new sources, open items.

## Reference

- [Scripts](https://claudecodekit.tansuasici.com/docs/scripts-ref): Utility scripts included in Claude Code Kit for health checks, validation, and more.
- [Hook Source Code](https://claudecodekit.tansuasici.com/docs/hook-source): Full source code for all built-in hooks included in Claude Code Kit.
- [Changelog](https://claudecodekit.tansuasici.com/docs/changelog): All notable changes to Claude Code Kit.

## Optional

- [Full content (llms-full.txt)](https://claudecodekit.tansuasici.com/llms-full.txt): every page concatenated for single-shot ingestion