{"id":50317003,"url":"https://github.com/vindm/dotclaude","last_synced_at":"2026-05-29T00:30:46.060Z","repository":{"id":359081224,"uuid":"1244411763","full_name":"vindm/dotclaude","owner":"vindm","description":"Most Claude Code plugins paste fixed templates. dotclaude reads your project, asks 5 smart questions, and authors a custom .claude/ from scratch — UX audit, a11y, design tokens, code review. Authored, not pasted.","archived":false,"fork":false,"pushed_at":"2026-05-20T12:43:52.000Z","size":398,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-20T13:04:04.150Z","etag":null,"topics":["accessibility","agent-skills","agentic-coding","ai-agents","anthropic-claude","claude-code","claude-code-plugin","claude-code-subagents","claude-skills","code-review","design-system","ux-design"],"latest_commit_sha":null,"homepage":"https://github.com/vindm/dotclaude","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/vindm.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"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":null,"dco":null,"cla":null}},"created_at":"2026-05-20T08:38:16.000Z","updated_at":"2026-05-20T12:59:33.000Z","dependencies_parsed_at":"2026-05-20T13:04:27.560Z","dependency_job_id":null,"html_url":"https://github.com/vindm/dotclaude","commit_stats":null,"previous_names":["vindm/dotclaude"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/vindm/dotclaude","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vindm%2Fdotclaude","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vindm%2Fdotclaude/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vindm%2Fdotclaude/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vindm%2Fdotclaude/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vindm","download_url":"https://codeload.github.com/vindm/dotclaude/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vindm%2Fdotclaude/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33632271,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-28T02:00:06.440Z","response_time":99,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["accessibility","agent-skills","agentic-coding","ai-agents","anthropic-claude","claude-code","claude-code-plugin","claude-code-subagents","claude-skills","code-review","design-system","ux-design"],"created_at":"2026-05-29T00:30:44.563Z","updated_at":"2026-05-29T00:30:46.042Z","avatar_url":"https://github.com/vindm.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"./assets/logo.svg\" width=\"560\" alt=\"dotclaude — AI dev infrastructure framework for Claude Code\"\u003e\n\n\u003cbr\u003e\n\n**AI dev infrastructure framework for Claude Code.**\n\nWalks you through 7 layers — project identity → architecture → process → quality bar → knowledge graph → domain kits → maintenance — and authors `CLAUDE.md` + `docs/` + `.claude/` derived from your project.\n\nNot templates. Not a kit. A **methodology**.\n\n\u003cbr\u003e\n\n\u003cimg src=\"./demo/bootstrap.gif\" width=\"900\" alt=\"/dotclaude:bootstrap walking the full 7-layer hierarchical interview, authoring CLAUDE.md + docs/ + .claude/ in ~30s on a fresh project\"\u003e\n\n\u003cbr\u003e\n\n[![Claude Code](https://img.shields.io/badge/Claude_Code-plugin-cc785c?style=for-the-badge)](https://docs.anthropic.com/claude-code/plugins)\n[![License](https://img.shields.io/badge/license-MIT-cc785c?style=for-the-badge)](LICENSE)\n[![Version](https://img.shields.io/badge/version-1.1.0-cc785c?style=for-the-badge)](#)\n\n\u003c/div\u003e\n\n\u003cbr\u003e\n\n```bash\nclaude plugin marketplace add vindm/dotclaude\nclaude plugin install dotclaude@dotclaude\n# Then in any project root:\n/dotclaude:bootstrap\n```\n\n# dotclaude — AI dev infrastructure for Claude Code\n\nA Claude Code plugin that bootstraps your project's `CLAUDE.md`, `docs/` knowledge graph, and `.claude/` system through a hierarchical interview. Distilled methodology from one battle-tested production codebase.\n\n**Jump to:** [Slash commands](#slash-commands) · [How it works](#how-it-works) · [See it in action](#see-it-in-action) · [What to expect](#what-to-expect) · [FAQ](#faq) · [Install](#install--contribute)\n\n\u003cbr\u003e\n\n## Slash commands\n\n| Command | What it sets up |\n|---|---|\n| 🪄 `/dotclaude:bootstrap` | **Headline.** Full 7-layer hierarchical interview. Authors `CLAUDE.md` + `docs/` + `.claude/`. |\n| 🎨 `/dotclaude:design` | **Showpiece.** UI / IA / a11y / visual-quality audit kit (Layer 6 standalone). |\n| 🧹 `/dotclaude:coding` | File-size discipline, code review, voice / forbidden phrases. |\n| 📐 `/dotclaude:planning` | Pre-impl validation, audit routing. |\n| 🧪 `/dotclaude:testing` | Test architecture + coverage strategy. |\n| 🗃️ `/dotclaude:data` | DB integrity, query discipline, migrations. |\n| 🤖 `/dotclaude:ai-workflow` | LLM cost monitoring + eval discipline. |\n| 🪄 `/dotclaude:init` | v1 entry — Layer 6 only, skips upstream layers. |\n\n**Inside the plugin** — 35 methodology principles · 12 hook templates · 7 domain skills + 1 bootstrap orchestrator · 4 anonymized war stories. Cost: ~984 tokens always-on per session; 2.7–5.5k per skill invocation; ~12k for full bootstrap. Full architectural reference in [`docs/v2-vision.md`](./docs/v2-vision.md).\n\n\u003cbr\u003e\n\n## How it works\n\n### The 7-layer hierarchy\n\nEach layer authors a specific slice of `CLAUDE.md` + `docs/` + `.claude/`. Dependency-ordered — Layer 1's output feeds Layers 2–6; Layer 7 polices the rest.\n\n| # | Layer | What bootstrap authors |\n|---|---|---|\n| 1 | **Project Identity** | `CLAUDE.md` opening — vision + ICP + moat + production-vs-internal + stage |\n| 2 | **Architecture** | `CLAUDE.md` Architecture + Constraints + boundary rules + universal hooks |\n| 3 | **Process Discipline** | `CLAUDE.md` \"How You Work\" + DoD + task-classification table + verification ladder + memory typing |\n| 4 | **Quality Bar** | `.claude/rules/design-north-star.md` (Tier 1 + Tier 2 benchmarks + anti-references) + `quality-bar` skill |\n| 5 | **Knowledge Graph** | `docs/README.md` + subdirectory skeleton + `docs/product/capabilities.md` scaffold |\n| 6 | **Domain Kits** | Per applicable domain: design / coding / planning / testing / data / ai-workflow. `.claude/{agents,skills,hooks,rules}/*` |\n| 7 | **Maintenance** | Saturday-style design-debt ritual + drift detection + `skill-auditor` agent (default-deferred for early projects) |\n\n### Bootstrap in 5 phases\n\n| Phase | What happens | Duration |\n|---|---|---|\n| 1. Project scan | Auto-discovers ~30–40% of inputs from `package.json`, file tree, `git log`, existing `CLAUDE.md` / `docs/` / `.claude/` | ~5s |\n| 2. Hierarchical interview | 7 phases (A–G), 1–3 Qs per turn, skip-if-Phase-1-answered | 20–60 min |\n| 3. Cross-layer coordination | Merges forbidden-phrase lists; reconciles audit routing | \u003c 1 min |\n| 4. Stage → review → commit | All authoring lands in `.claude-staging/` first; explicit approval gate | varies |\n| 5. Output summary | Inventory by layer + skipped reasons + next-step recommendations | \u003c 30s |\n\n### Brownfield safety\n\nBootstrap detects your project's state via Phase 1 scan and runs in the right mode automatically.\n\n| Project state | Mode | What bootstrap does |\n|---|---|---|\n| No `CLAUDE.md` + no `.claude/` | **Fresh** | Runs all 7 layers |\n| `CLAUDE.md` \u003c 50 LOC OR `.claude/` \u003c 5 artifacts | **APPEND** | Adds missing layers only; never stomps existing |\n| `CLAUDE.md` \u003e 200 LOC OR \u003e 5 H2s + structured | **REFUSE** | Recommends Layer 6 standalone or manual edits |\n\nREFUSE is a feature — it protects accumulated AI infrastructure from being overwritten.\n\n\u003cbr\u003e\n\n## See it in action\n\n`/dotclaude:design` running on a fresh Vite + React + TypeScript project, authoring 8 tailored design artifacts (4 agents + 2 skills + 2 hooks) in ~15 seconds:\n\n\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"./demo/demo.gif\" width=\"900\" alt=\"/dotclaude:design — Layer 6 design kit authored fresh for a Vite + React + Tailwind project with Linear + Stripe Dashboard benchmarks\"\u003e\n\n\u003c/div\u003e\n\n**Validation reports** (real runs, not simulations):\n- [Bootstrap on a battle-tested production codebase](./docs/bootstrap-smoke-test-2026-05-21.md) — full 7-layer flow, ~65% depth match\n- [`/dotclaude:design` on a fresh Vite + React project](./docs/design-real-smoke-test-2026-05-21.md) — grade **A**\n- [`/dotclaude:coding` on the same fresh project](./docs/coding-real-smoke-test-2026-05-21.md) — grade **A-minus**\n\n\u003cbr\u003e\n\n## What to expect\n\n**Wall-clock per project shape:**\n\n| Project shape | Bootstrap time |\n|---|---|\n| Greenfield, 1–3 domains | 20–35 min |\n| Early prototype, 3–5 domains | 40–60 min |\n| Shipped, 5–7 domains | 60–90 min |\n| Mature, 8 domains (max-domain) | 90–120 min |\n| Brownfield comprehensive (REFUSE) | \u003c 5 min, no authoring |\n\n**What bootstrap can't manufacture in one pass:**\n\n- **Accumulated incident memories** — emerge from coding sessions over weeks/months\n- **Per-aspect design system docs** — land when content emerges from real design work\n- **Substrate runbook skills** — written when you've lost \u003e 1 hour relearning a subsystem twice\n\nBootstrap creates the scaffold + the \"accrue-here\" anchors. The entries themselves accumulate over time. The methodology compounds; one-pass output is the seed, not the tree.\n\nFull depth-match analysis: [`docs/bootstrap-smoke-test-2026-05-21.md`](./docs/bootstrap-smoke-test-2026-05-21.md).\n\n\u003cbr\u003e\n\n## FAQ\n\n**How is this different from a `CLAUDE.md` template?**\n\nTemplates are static text you paste + edit. dotclaude reads your actual project (`package.json`, file tree, `git log --grep=\"fix:\"`, existing conventions) and **authors** a `CLAUDE.md` tuned to it. The 7 layers are a methodology, not a template.\n\n**Will dotclaude overwrite my existing `CLAUDE.md` or `.claude/`?**\n\nNo. Phase 1 scan detects existing infrastructure. Mature setups trigger REFUSE mode (recommends Layer 6 standalone instead). Partial setups trigger APPEND mode (adds missing layers only, never stomps). All authoring goes to `.claude-staging/` first; explicit approval gate before commit.\n\n**Does it work for non-iOS / non-React-Native projects?**\n\nYes. The methodology is platform-agnostic. Smoke tested on a Vite + React + TypeScript + Tailwind project — grade A. The 7 layers map to any project shape; the domain skills (`/dotclaude:coding`, `/dotclaude:data`, etc.) are stack-universal.\n\n**Can I use just one domain skill without bootstrap?**\n\nYes. `/dotclaude:design`, `/dotclaude:coding`, or any other domain skill runs standalone. Useful for incremental setup or adding a new concern to an existing `CLAUDE.md`.\n\n**What does it cost in tokens?**\n\n~984 tokens always-on per session (skill descriptions). 2.7–5.5k per single skill invocation. ~12k for the full bootstrap (loads upstream principles selectively per layer). Session overhead is \u003c 1% of typical Claude usage.\n\n**How do I uninstall?**\n\n`claude plugin uninstall dotclaude@dotclaude`. The `.claude/` directory dotclaude authored stays in your project — it's yours to edit, version, or remove.\n\n\u003cbr\u003e\n\n## Install \u0026 contribute\n\n```bash\n# Production install (any Claude Code session)\nclaude plugin marketplace add vindm/dotclaude\nclaude plugin install dotclaude@dotclaude\n\n# Dev install (for contributing)\ngit clone https://github.com/vindm/dotclaude.git \u0026\u0026 cd dotclaude\nclaude --plugin-dir .\n```\n\n**Contributing**: full guide in [**CONTRIBUTING.md**](./CONTRIBUTING.md) — covers adding principles, hooks, skills, war stories, smoke test discipline, and the PR checklist.\n\n**Changelog**: see [CHANGELOG.md](./CHANGELOG.md) for v1.0.0 → v1.1.0 (v2 reframe).\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n\u003csub\u003eBuilt from months of working with Claude Code as a daily driver.\u003c/sub\u003e\u003cbr\u003e\n\u003csub\u003eMIT licensed · \u003ca href=\"./docs/v2-vision.md\"\u003ev2 architecture\u003c/a\u003e · \u003ca href=\"./CHANGELOG.md\"\u003echangelog\u003c/a\u003e · \u003ca href=\"./CONTRIBUTING.md\"\u003econtribute\u003c/a\u003e\u003c/sub\u003e\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvindm%2Fdotclaude","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvindm%2Fdotclaude","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvindm%2Fdotclaude/lists"}