{"id":47810000,"url":"https://github.com/tansuasici/claude-code-kit","last_synced_at":"2026-05-16T02:14:43.329Z","repository":{"id":342065332,"uuid":"1172614225","full_name":"tansuasici/claude-code-kit","owner":"tansuasici","description":"Drop-in starter templates that make Claude Code behave like a disciplined staff engineer instead of an eager intern.","archived":false,"fork":false,"pushed_at":"2026-04-14T11:03:16.000Z","size":343,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-14T11:28:03.789Z","etag":null,"topics":["ai-agent","claude","claude-code","developer-tools","starter-kit"],"latest_commit_sha":null,"homepage":"https://claudecodekit.tansuasici.com","language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tansuasici.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-03-04T14:05:57.000Z","updated_at":"2026-04-14T11:03:10.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/tansuasici/claude-code-kit","commit_stats":null,"previous_names":["tansuasici/claude-code-kit"],"tags_count":14,"template":false,"template_full_name":null,"purl":"pkg:github/tansuasici/claude-code-kit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tansuasici%2Fclaude-code-kit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tansuasici%2Fclaude-code-kit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tansuasici%2Fclaude-code-kit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tansuasici%2Fclaude-code-kit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tansuasici","download_url":"https://codeload.github.com/tansuasici/claude-code-kit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tansuasici%2Fclaude-code-kit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32291347,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-26T08:29:33.829Z","status":"ssl_error","status_checked_at":"2026-04-26T08:29:18.366Z","response_time":129,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agent","claude","claude-code","developer-tools","starter-kit"],"created_at":"2026-04-03T18:06:47.410Z","updated_at":"2026-05-12T02:05:22.829Z","avatar_url":"https://github.com/tansuasici.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/logo.png\" alt=\"Claude Code Kit\" width=\"160\"\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003eClaude Code Kit\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003eDrop-in starter templates that make Claude Code behave like a disciplined staff engineer instead of an eager intern.\u003c/p\u003e\n\n## The Problem\n\nOut of the box, Claude Code is powerful but undisciplined. It will:\n- Start coding before understanding the codebase\n- Make sweeping changes across files you didn't ask it to touch\n- Skip verification steps and ship broken code\n- Forget lessons from previous mistakes\n- Install dependencies and change architecture without asking\n\n## The Solution\n\nThis kit provides a `CLAUDE.md` instruction set and supporting templates that enforce a structured workflow:\n\n**Plan \u003e Confirm \u003e Implement \u003e Verify** — every single time.\n\n## Quick Start\n\n```bash\nnpx @tansuasici/claude-code-kit init\n```\n\nOr with curl:\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/tansuasici/claude-code-kit/main/install.sh | bash\n```\n\nThen fill in `CODEBASE_MAP.md` with your project's details and start a Claude Code session.\n\n### Installer options\n\n| Flag | Description |\n|------|-------------|\n| `--template nextjs` | Use a stack-specific template (`nextjs`, `node-api`, `python-fastapi`). Auto-detected if omitted. |\n| `--profile minimal` | Hooks only, no CLAUDE.md or docs |\n| `--profile strict` | All hooks enabled (auto-lint, auto-format, skill-extract-reminder) |\n| `--upgrade` | Add new files without overwriting your customizations |\n| `--diff` | Compare local installation against latest kit (read-only) |\n| `--gitignore` | Add kit files to `.gitignore` (keep kit local, don't push to repo) |\n| `--wiki` | Add knowledge wiki module (personal knowledge base) |\n| `--html` | Add HTML artifacts module (specs, reports, PR writeups as HTML — see `ARTIFACTS.md`) |\n| `--version v1.0.0` | Install a specific version instead of latest |\n\n### Uninstall\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/tansuasici/claude-code-kit/main/uninstall.sh | bash\n```\n\n| Flag | Description |\n|------|-------------|\n| `--dry-run` | Show what would be removed without deleting |\n| `--keep-tasks` | Preserve `tasks/` directory (lessons, decisions, handoffs) |\n| `--keep-project` | Preserve project overlay files (`CLAUDE.project.md`, `agent_docs/project/`, etc.) |\n| `--force` | Remove without confirmation |\n\nExamples:\n\n```bash\n# Install with npx\nnpx @tansuasici/claude-code-kit init --template nextjs\nnpx @tansuasici/claude-code-kit init --profile strict\nnpx @tansuasici/claude-code-kit init --wiki\nnpx @tansuasici/claude-code-kit init --html\nnpx @tansuasici/claude-code-kit init --upgrade\n\n# Or with curl\ncurl -fsSL .../install.sh | bash -s -- --template nextjs\ncurl -fsSL .../install.sh | bash -s -- --gitignore\ncurl -fsSL .../install.sh | bash -s -- --upgrade\ncurl -fsSL .../install.sh | bash -s -- --diff\ncurl -fsSL .../install.sh | bash -s -- --version v1.0.0\n```\n\n### npx CLI commands\n\n```bash\nnpx @tansuasici/claude-code-kit init              # Install kit\nnpx @tansuasici/claude-code-kit doctor            # Check installation health\nnpx @tansuasici/claude-code-kit convert all       # Export to Cursor/Windsurf/Aider/AGENTS.md\nnpx @tansuasici/claude-code-kit generate agents-md  # Generate AGENTS.md only\nnpx @tansuasici/claude-code-kit --version         # Show version\n```\n\n\u003cdetails\u003e\n\u003csummary\u003eManual install\u003c/summary\u003e\n\n```bash\ngit clone --depth 1 https://github.com/tansuasici/claude-code-kit.git /tmp/cck\ncp /tmp/cck/CLAUDE.md /tmp/cck/CODEBASE_MAP.md /tmp/cck/CLAUDE.project.md .\ncp -r /tmp/cck/agent_docs /tmp/cck/tasks /tmp/cck/scripts /tmp/cck/.claude .\nrm -rf /tmp/cck\n```\n\n\u003c/details\u003e\n\n## What CLAUDE.md Enforces\n\n| Rule | What it does |\n|------|-------------|\n| **Tiered Session Boot** | Loads context in 3 tiers (always → if continuing → on demand) to minimize token overhead |\n| **Plan First** | Writes a plan for multi-file changes, waits for your confirmation |\n| **Scope Discipline** | Touches only what's needed, logs unrelated issues in \"Not Now\" |\n| **Protected Changes** | Stops for approval on deps, schema, auth, API, and build changes |\n| **Verification** | Typecheck, lint, test, smoke test — in that order, every time |\n| **Self-Improvement** | Logs corrections to `tasks/lessons/` (one file per lesson) and reviews `_index.md` Top Rules each session |\n\n## Before / After\n\n\u003cdetails\u003e\n\u003csummary\u003eWithout the kit\u003c/summary\u003e\n\n```text\nYou: \"Add a search feature to the users page\"\n\nClaude: *immediately starts coding*\n  - Installs 3 new packages without asking\n  - Refactors the entire users module \"while it's here\"\n  - Breaks the build because it didn't typecheck\n  - Doesn't test anything\n  - You spend 30 minutes reviewing and reverting unrelated changes\n```\n\n\u003c/details\u003e\n\n\u003cdetails open\u003e\n\u003csummary\u003eWith the kit\u003c/summary\u003e\n\n```text\nYou: \"Add a search feature to the users page\"\n\nClaude: \"Let me restate: add search functionality to the users page.\nI've read CODEBASE_MAP.md — the users page is at app/(dashboard)/users/page.tsx,\ndata comes from src/services/user.service.ts.\n\nThis touches 3+ files, so here's my plan:\"\n\n  ## Task: Add search to users page\n  ### Approach\n  1. Add search param handling in users/page.tsx\n  2. Add `searchUsers()` to user.service.ts\n  3. Add search input component\n  ### Files to Touch\n  - app/(dashboard)/users/page.tsx\n  - src/services/user.service.ts\n  - components/features/user-search.tsx (new)\n\n  \"Should I proceed with this plan?\"\n\nYou: \"Yes\"\n\nClaude: *implements, then runs:*\n  1. tsc --noEmit ✓\n  2. eslint ✓\n  3. npm test ✓\n  4. Opens the page, verifies search works ✓\n\n  \"Done. All verification passed.\"\n```\n\n\u003c/details\u003e\n\n## Hooks\n\nHooks are shell scripts that run automatically — unlike CLAUDE.md rules (advisory), hooks are **deterministic**.\n\n| Hook | Type | What it does |\n|------|------|-------------|\n| `protect-files` | PreToolUse | Blocks edits to `.env`, credentials, private keys, lock files |\n| `branch-protect` | PreToolUse | Blocks push to `main`/`master` and force pushes |\n| `block-dangerous-commands` | PreToolUse | Blocks `rm -rf /`, `git reset --hard`, `DROP TABLE`, etc. |\n| `conventional-commit` | PreToolUse | Enforces `feat:`, `fix:`, `refactor:` commit message format |\n| `secret-scan` | PostToolUse | Warns if API keys, tokens, or passwords are found |\n| `unicode-scan` | PostToolUse | Detects invisible Unicode (Glassworm supply chain attack defense) |\n| `loop-detect` | PostToolUse | Detects edit loops — warns at 4, blocks at 6 edits to the same file |\n| `task-complete-notify` | Stop | Desktop notification + sound when Claude finishes |\n| `auto-lint` | PostToolUse | Runs linter after edits *(opt-in)* |\n| `auto-format` | PostToolUse | Runs formatter after edits *(opt-in)* |\n| `skill-compliance` | PostToolUse | Checks edited files against active skill checklists *(opt-in)* |\n| `skill-extract-reminder` | UserPromptSubmit | Reminds to extract discoveries as skills *(opt-in)* |\n\nOpt-in hooks are not enabled by default — they can be slow or conflict with project configs. See `agent_docs/hooks.md` for how to enable them and write your own.\n\n## Agents\n\nBuilt-in agents for code review, planning, and maintenance:\n\n| Agent | What it does |\n|-------|-------------|\n| `code-reviewer` | Reviews for correctness, quality, and best practices |\n| `security-reviewer` | Scans code for vulnerabilities and security issues |\n| `qa-reviewer` | Evidence-based QA verification |\n| `planner` | Creates implementation plans with 3-lens review and failure modes |\n| `dead-code-remover` | Removes verified unused code through static reference analysis |\n| `wiki-maintainer` | Knowledge wiki maintenance — ingest, cross-reference, health checks *(requires `--wiki`)* |\n\n## Skills\n\nUser-invocable audit and guide skills — run with `/skill-name`:\n\n| Skill | What it does |\n|-------|-------------|\n| `/code-quality-audit` | Audits code smells, error handling, and maintainability |\n| `/performance-audit` | Identifies bottlenecks in startup, rendering, memory, and I/O |\n| `/architecture-review` | Reviews SOLID compliance, module boundaries, and dependencies |\n| `/deepening-review` | Depth/seam paradigm — surfaces shallow modules and grills the chosen one interactively |\n| `/interface-design` | Design It Twice — parallel sub-agents produce competing interfaces, then compare |\n| `/testing-audit` | Audits test coverage, quality, and testing strategy |\n| `/dead-code-audit` | Detects unused functions, dead imports, and orphan files |\n| `/refactoring-guide` | Fowler-based refactoring recommendations with execution plans |\n| `/accessibility-audit` | WCAG 2.1 AA compliance audit for UI code |\n| `/dependency-audit` | Checks dependencies for vulnerabilities, licenses, and bloat |\n| `/documentation-audit` | Audits inline docs, API docs, and README quality |\n| `/project-health-report` | Comprehensive multi-dimensional project health report |\n| `/ship` | Full deployment pipeline — tests, coverage, CHANGELOG, bisectable commits, PR |\n| `/retro` | Weekly retrospective with session analytics and LOC metrics |\n| `/office-hours` | Pre-coding product validation — clarify what and why before coding |\n| `/debug` | Systematic root-cause debugging with evidence-before-fix enforcement |\n| `/design-review` | UI design consistency, AI slop detection, and responsive behavior |\n| `/skill-extractor` | Extracts non-obvious knowledge into reusable skills *(supports `mode:headless`)* |\n| `/skill-generator` | Generates project-specific coding skills from tech stack analysis |\n| `/shape-spec` | Creates timestamped feature spec folders for multi-session planning |\n| `/review-pipeline` | Runs multiple audits in parallel over a PR-scope diff, dedupes findings, and saves a confidence-gated report *(supports `mode:headless`)* |\n| `/lesson-refresh` | Periodic refresh of `tasks/lessons/` — keep / update / promote / encode / archive verdicts *(supports `mode:headless`)* |\n| `/pulse` | Time-windowed outcome report saved to `tasks/pulses/` — what shipped, broke, was learned, is open *(supports `mode:headless`)* |\n| `/wiki-ingest` | Ingest source into knowledge wiki — summarize, cross-reference, update index *(requires `--wiki`)* |\n| `/wiki-lint` | Health-check the knowledge wiki — contradictions, orphans, stale content *(requires `--wiki`)* |\n| `/wiki-briefing` | Morning briefing from the wiki — recent activity, new sources, open items *(requires `--wiki`)* |\n\n## Stack Templates\n\nEach template includes a customized `CLAUDE.md` with stack-specific rules and a pre-filled `CODEBASE_MAP.md`:\n\n| Template | Stack | Includes |\n|----------|-------|----------|\n| `nextjs` | Next.js 16, App Router, Prisma, Tailwind | Server/Client Component rules, build verification |\n| `node-api` | Express, TypeScript, Knex.js | Layered architecture, API design conventions |\n| `python-fastapi` | FastAPI, SQLAlchemy 2.0, Pydantic v2 | Async patterns, dependency injection, Alembic |\n\n## Scripts\n\n| Script | What it does |\n|--------|-------------|\n| `./scripts/doctor.sh` | Checks installation health (missing files, broken hooks, invalid settings) |\n| `./scripts/validate.sh` | Checks `CODEBASE_MAP.md` for unfilled placeholders |\n| `./scripts/statusline.sh` | Terminal status line showing model, branch, context %, cost |\n| `./scripts/convert.sh` | Exports agents to Cursor, Windsurf, Aider, and AGENTS.md formats |\n| `./scripts/gen-agents-md.sh` | Generates cross-tool AGENTS.md from project sources |\n| `./scripts/validate-skills.sh` | Validates skill directory structure |\n| `./scripts/gen-skill-docs.sh` | Generates web MDX docs from SKILL.md files |\n| `./scripts/build-skills.sh` | Builds SKILL.md from `.tmpl` templates + shared blocks |\n| `./scripts/migrate-lessons.sh` | One-time migration from legacy `tasks/lessons.md` to per-file `tasks/lessons/` structure |\n\n### Status line setup\n\nAdd to `.claude/settings.json`:\n\n```json\n{\n  \"statusLine\": {\n    \"command\": \"./scripts/statusline.sh\"\n  }\n}\n```\n\n```text\nsonnet-4.5 | feat/search | ████████░░ 78% | $1.24\n```\n\n## Features\n\n**AGENTS.md Export** — Generate a cross-tool [AGENTS.md](https://agents.md/) file from your project configuration. Compatible with GitHub Copilot, OpenAI Codex, Cursor, Google Jules, and Aider. Source of truth remains `CLAUDE.md` — AGENTS.md is a one-way derived output.\n\n**Tiered Session Boot** — Context loads in 3 tiers to minimize token overhead: Tier 1 (always: project map + overlay), Tier 2 (if continuing: handoff + todo), Tier 3 (on demand: lessons top rules, decisions). Reduces startup token cost ~40-50%.\n\n**npx Distribution** — Install and manage the kit with `npx @tansuasici/claude-code-kit init`. Supports init, upgrade, doctor, convert, and generate commands.\n\n**Session Handoff** — Long sessions lose context. Before ending, Claude generates `tasks/handoff-[date].md`. The next session reads it and resumes where you left off.\n\n**Skill Extraction** — Claude discovers non-obvious things during sessions (framework quirks, workarounds, config gotchas). The skill system captures these as `.claude/skills/\u003cname\u003e/SKILL.md` files that load automatically via semantic matching. Run `/skill-extractor` to review.\n\n**Architecture Decision Records** — When Claude presents options and you pick one, the reasoning gets recorded in `tasks/decisions.md` as ADRs with context, options, and consequences.\n\n**DESIGN.md** — Optional design system template for UI projects. Captures colors, typography, spacing, component styles in a format agents read natively. The `/design-review` skill checks implementation against it.\n\n**Knowledge Wiki** — Optional knowledge wiki module (install with `--wiki`). Based on Andrej Karpathy's LLM Wiki pattern: Claude incrementally builds and maintains a persistent, interlinked wiki from raw sources. Three operations: `/wiki-ingest` processes new sources into the wiki, `/wiki-lint` health-checks for contradictions and orphans, `/wiki-briefing` gives you a daily summary. The wiki compounds — every source you add makes it smarter.\n\n**HTML Artifacts** — Optional module (install with `--html`). Based on the Claude Code team's pattern of preferring HTML output over markdown for specs, plans, PR writeups, reports, and design prototypes — richer information (SVG, tables, code, interactions), easier to share (upload + link), and easier to read for anyone outside your terminal. The kit ships `ARTIFACTS.md` (conventions) and a `design-system.html` reference so every generated artifact stays on-brand. Deliberately ships *without* a `/html` skill — the original recommendation is to just prompt for HTML, not to over-structure it.\n\n**Product Context** — Optional templates in `agent_docs/project/` (mission.md, tech-stack.md, roadmap.md) give agents product awareness beyond code conventions.\n\n**Permissions** — `.claude/settings.json` includes curated allow/deny lists. Allowed: test runners, linters, git reads. Denied: `curl`, `wget`, `.env` reads, `npm publish`. Review and customize for your project.\n\n**Project Overlay** — Separate kit-managed files from project-specific customizations. `CLAUDE.project.md`, `agent_docs/project/`, and `.claude/hooks/project/` are never touched by kit upgrades, so your project rules survive `--upgrade` cleanly.\n\n## What's Inside\n\n\u003cdetails\u003e\n\u003csummary\u003eFull directory structure\u003c/summary\u003e\n\n```text\nclaude-code-kit/\n  CLAUDE.md                        # Core agent instructions (kit-managed)\n  CLAUDE.project.md                # Project-specific overlay (yours, never overwritten)\n  CODEBASE_MAP.md                  # Project mapping template\n  AGENTS.md                        # Cross-tool standard (generated by gen-agents-md.sh)\n  package.json                     # npm package definition (for npx distribution)\n  .kit-manifest                    # Tracks kit-managed files (auto-generated)\n  install.sh                       # One-line setup script\n  uninstall.sh                     # Clean removal script\n  bin/\n    claude-code-kit.js             # Node.js entry point for npx\n    cli.sh                         # Shell CLI implementation\n  agent_docs/                      # Agent behavior guides\n    workflow.md                    #   Planning templates \u0026 task lifecycle\n    debugging.md                   #   4-step debugging protocol\n    testing.md                     #   Test strategy \u0026 patterns\n    conventions.md                 #   Naming, structure, git hygiene\n    subagents.md                   #   When \u0026 how to use subagents\n    hooks.md                       #   Hooks guide \u0026 how to write your own\n    skills.md                      #   Skill extraction guide\n    contracts.md                   #   Task contract system\n    prompting.md                   #   Bias awareness \u0026 neutral prompting\n    architecture-language.md       #   Vocabulary for /deepening-review and /interface-design\n    project/                       #   Project-specific docs (yours)\n  tasks/                           # Session state \u0026 tracking\n    todo.md, decisions.md, handoff.md\n    lessons/                       #   Per-file lessons (YAML frontmatter)\n      _index.md                    #     Top Rules + per-lesson links\n      _TEMPLATE.md                 #     Template for new lessons\n      \u003cYYYY-MM-DD\u003e-\u003cslug\u003e.md       #     One file per lesson\n  scripts/                         # Utility scripts\n    doctor.sh, validate.sh, statusline.sh, convert.sh, validate-skills.sh, build-skills.sh, gen-skill-docs.sh, gen-agents-md.sh\n  # --- Optional: Knowledge Wiki (--wiki) ---\n  WIKI.md                          # Wiki schema \u0026 conventions\n  raw-sources/                     # Immutable source documents (yours)\n  wiki/                            # Claude-maintained knowledge base\n    index.md, log.md               # Navigation \u0026 activity log\n    summaries/, entities/, concepts/ # Wiki page directories\n  # --- Optional: HTML Artifacts (--html) ---\n  ARTIFACTS.md                     # HTML artifact conventions \u0026 schema\n  artifacts/                       # Generated HTML artifacts\n    design-system.html             # Reference tokens — every artifact mirrors these\n    index.html                     # Catalog of all artifacts\n  .claude/\n    settings.json                  # Hook configs \u0026 permissions\n    agents/                        # code-reviewer, security-reviewer, planner, qa-reviewer, dead-code-remover, wiki-maintainer\n    hooks/                         # 12 deterministic hook scripts\n      project/                     # Project-specific hooks (yours)\n    skills/                        # Reusable knowledge \u0026 audit skills\n      _shared/blocks/              # Shared template blocks (preamble, scope, etc.)\n      _templates/                  # .tmpl skill templates (source of truth)\n      skill-extractor/             # Meta-skill for knowledge extraction\n      skill-generator/             # Meta-skill for generating project skills\n      code-quality-audit/          # Code smells \u0026 error handling audit\n      performance-audit/           # Bottleneck \u0026 rendering analysis\n      architecture-review/         # SOLID \u0026 module boundary review\n      deepening-review/            # Depth/seam paradigm — interactive candidate grilling\n      interface-design/            # Design It Twice — parallel competing interfaces\n      testing-audit/               # Test coverage \u0026 quality audit\n      dead-code-audit/             # Unused code detection\n      refactoring-guide/           # Fowler-based refactoring plans\n      accessibility-audit/         # WCAG 2.1 AA compliance\n      dependency-audit/            # Vulnerability \u0026 license checks\n      documentation-audit/         # Doc quality \u0026 sync audit\n      project-health-report/       # Comprehensive health report\n      ship/                        # Deployment pipeline\n      retro/                       # Sprint retrospective \u0026 analytics\n      office-hours/                # Pre-coding product validation\n      debug/                       # Root-cause debugging\n      design-review/               # UI design consistency review\n      shape-spec/                  # Feature spec folder creation\n      wiki-ingest/                 # Wiki source ingestion (--wiki)\n      wiki-lint/                   # Wiki health checks (--wiki)\n      wiki-briefing/               # Wiki daily briefing (--wiki)\n  examples/\n    nextjs/                        # Next.js 16 + App Router template\n    node-api/                      # Express + TypeScript template\n    python-fastapi/                # FastAPI + SQLAlchemy template\n```\n\n\u003c/details\u003e\n\n## Project Overlay\n\nThe kit separates **kit-managed files** (updated by `--upgrade`) from **project-specific files** (never touched):\n\n| Layer | Files | Managed by |\n|-------|-------|------------|\n| Kit base | `CLAUDE.md`, `agent_docs/*.md`, `.claude/hooks/*.sh` | `install.sh --upgrade` |\n| Project overlay | `CLAUDE.project.md`, `agent_docs/project/`, `.claude/hooks/project/` | You |\n\nProject rules in `CLAUDE.project.md` override kit defaults. Add project-specific docs (offline-first patterns, SignalR conventions, etc.) to `agent_docs/project/` and project-specific hooks to `.claude/hooks/project/`.\n\nThe `.kit-manifest` file tracks which files are kit-managed, so upgrades know what to update and what to skip.\n\n## Customization\n\nThis kit is a starting point. You should:\n\n1. **Fill in `CODEBASE_MAP.md`** — the more detail, the better Claude performs\n2. **Customize `CLAUDE.project.md`** — add project-specific rules, constraints, and patterns\n3. **Add project docs** — put stack-specific guides in `agent_docs/project/`\n4. **Track lessons** — `tasks/lessons/` compounds over time (one file per lesson, with YAML frontmatter and a Top Rules index), making Claude smarter per-project\n\n## Contributing\n\nPRs welcome. If you've built a template for a stack we don't cover yet, open a PR.\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftansuasici%2Fclaude-code-kit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftansuasici%2Fclaude-code-kit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftansuasici%2Fclaude-code-kit/lists"}