{"id":45767580,"url":"https://github.com/jhlee0409/all-for-claudecode","last_synced_at":"2026-04-01T19:28:14.951Z","repository":{"id":339339087,"uuid":"1161292145","full_name":"jhlee0409/all-for-claudecode","owner":"jhlee0409","description":"Claude Code plugin — automates the full dev cycle (spec → plan → implement → review → clean) with critic loops, 8 domain expert consultants, and safety guards. Zero dependencies.","archived":false,"fork":false,"pushed_at":"2026-03-07T10:13:48.000Z","size":736,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-07T15:03:36.359Z","etag":null,"topics":["agentic-coding","ai-coding","anthropic","automation","ci-cd","claude-code","claude-code-plugin","claude-code-plugins","code-review","developer-tools","development-workflow","expert-consultation","hooks","pipeline","quality-gates","shell-script","slash-commands","spec-driven-development","task-orchestration","workflow-automation"],"latest_commit_sha":null,"homepage":"https://www.npmjs.com/package/all-for-claudecode","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/jhlee0409.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":".github/SECURITY.md","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},"funding":{"github":"jhlee0409"}},"created_at":"2026-02-19T00:08:43.000Z","updated_at":"2026-03-07T10:13:52.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/jhlee0409/all-for-claudecode","commit_stats":null,"previous_names":["jhlee0409/selfish-pipeline","jhlee0409/all-for-claudecode"],"tags_count":15,"template":false,"template_full_name":null,"purl":"pkg:github/jhlee0409/all-for-claudecode","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jhlee0409%2Fall-for-claudecode","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jhlee0409%2Fall-for-claudecode/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jhlee0409%2Fall-for-claudecode/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jhlee0409%2Fall-for-claudecode/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jhlee0409","download_url":"https://codeload.github.com/jhlee0409/all-for-claudecode/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jhlee0409%2Fall-for-claudecode/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30329697,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-10T05:25:20.737Z","status":"ssl_error","status_checked_at":"2026-03-10T05:25:17.430Z","response_time":106,"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":["agentic-coding","ai-coding","anthropic","automation","ci-cd","claude-code","claude-code-plugin","claude-code-plugins","code-review","developer-tools","development-workflow","expert-consultation","hooks","pipeline","quality-gates","shell-script","slash-commands","spec-driven-development","task-orchestration","workflow-automation"],"created_at":"2026-02-26T02:58:07.363Z","updated_at":"2026-04-01T19:28:14.940Z","avatar_url":"https://github.com/jhlee0409.png","language":"Shell","funding_links":["https://github.com/sponsors/jhlee0409"],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e                                                                                                                                        \n  \u003cimg src=\"https://github.com/user-attachments/assets/ce9a12a0-5554-425e-ae8a-efa098bfb70e\" alt=\"all-for-claudecode\" width=\"1080\" /\u003e\n\u003c/div\u003e\n\n# all-for-claudecode\n\n**Claude Code plugin that automates the full development cycle — spec → plan → implement → review → clean.**\n\n[![CI](https://github.com/jhlee0409/all-for-claudecode/actions/workflows/ci.yml/badge.svg)](https://github.com/jhlee0409/all-for-claudecode/actions/workflows/ci.yml)\n[![npm version](https://img.shields.io/npm/v/all-for-claudecode)](https://www.npmjs.com/package/all-for-claudecode)\n[![npm downloads](https://img.shields.io/npm/dm/all-for-claudecode)](https://www.npmjs.com/package/all-for-claudecode)\n[![license](https://img.shields.io/github/license/jhlee0409/all-for-claudecode)](./LICENSE)\n[![GitHub stars](https://img.shields.io/github/stars/jhlee0409/all-for-claudecode?style=social)](https://github.com/jhlee0409/all-for-claudecode)\n\n\u003e One command (`/afc:auto`) runs the entire cycle. Zero runtime dependencies — pure markdown commands + bash hook scripts.\n\n## Quick Start\n\n```bash\n# Option A: Inside Claude Code\n/plugin marketplace add jhlee0409/all-for-claudecode\n/plugin install afc@all-for-claudecode\n\n# Option B: npx\nnpx all-for-claudecode\n```\n\nThen:\n\n```\n/afc:setup                             # Set up global routing in ~/.claude/CLAUDE.md\n/afc:init                              # Detect your stack, generate project config\n/afc:auto \"Add user authentication\"    # Run the full pipeline\n```\n\nThe pipeline will:\n1. Write a feature spec with acceptance criteria\n2. Design an implementation plan with file change map\n3. Implement tasks with CI gates (auto task decomposition + parallel execution)\n4. Run code review with architecture/security agent analysis\n5. Clean up artifacts and prepare for commit\n\n## How It Works\n\n```\n/afc:auto \"Add feature X\"\n\nSpec (1/5) → Plan (2/5) → Implement (3/5) → Review (4/5) → Clean (5/5)\n  │              │              │                │              │\n  │              │              │                │              └─ Artifact cleanup\n  │              │              │                └─ 8 perspectives + agent review\n  │              │              └─ Auto task decomposition, parallel execution, CI gates\n  │              └─ File change map, ADR recording, research persistence\n  └─ Acceptance criteria, pre-implementation gates\n\nSkill Advisor checkpoints (A–E) between phases dynamically invoke\nauxiliary skills (ideate, consult, architect, security, test, qa, learner)\nwhen LLM evaluation detects they would add value. Budget: max 5 per run.\n\nHooks run automatically at each step.\nCI failure → debug-based RCA (not blind retry).\nCritic Loops verify quality at each gate until convergence.\n```\n\n## Walkthrough: What a Pipeline Run Looks Like\n\nRunning `/afc:auto \"Add password reset flow\"` produces this (abbreviated):\n\n**Spec (1/5)** — Generates `spec.md` with requirements and acceptance criteria:\n```\nFR-001: POST /auth/reset sends email with token\nFR-002: GET /auth/reset/:token validates and shows form\nFR-003: Token expires after 1 hour\nAcceptance: Given expired token, When user submits, Then show error\n```\n\n**Plan (2/5)** — Creates `plan.md` with file change map and architecture decisions:\n```\nFile Change Map:\n  src/routes/auth.ts        — ADD reset endpoint handlers\n  src/services/email.ts     — ADD sendResetEmail()\n  src/middleware/validate.ts — MODIFY add token validation\n  tests/auth.test.ts        — ADD reset flow tests\n```\n\n**Implement (3/5)** — Auto-decomposes into tasks, executes with CI gates:\n```\nTasks: 4 total (2 parallel)\n  [1] Add reset endpoint     ✓\n  [2] Add email service       ✓  ← parallel with [1]\n  [3] Add token validation    ✓  ← depends on [1]\n  [4] Add tests               ✓\nCI: npm test → passed\n```\n\n**Review (4/5)** — 8-perspective review + specialist agent analysis:\n```\nArchitecture (afc-architect): ✓ layer boundaries respected\nSecurity (afc-security): ⚠ rate-limit reset endpoint\nPerformance: ✓ no N+1 queries\n→ Auto-fixed: added rate limiter middleware\n```\n\n**Clean (5/5)** — Removes pipeline artifacts, final CI check.\n\n## Slash Commands\n\n| Command | Description |\n|---|---|\n| `/afc:auto` | Full Auto pipeline — runs all 5 phases |\n| `/afc:spec` | Write feature specification with acceptance criteria |\n| `/afc:plan` | Design implementation plan with file change map |\n| `/afc:implement` | Execute code implementation with CI gates |\n| `/afc:test` | Test strategy planning and test writing |\n| `/afc:review` | Code review with architecture/security scanning |\n| `/afc:clean` | Pipeline artifact cleanup and codebase hygiene |\n| `/afc:research` | Technical research with persistent storage |\n| `/afc:debug` | Bug diagnosis and fix |\n| `/afc:init` | Project setup — detects stack and generates project config |\n| `/afc:setup` | Global CLAUDE.md configuration — injects/updates AFC routing block |\n| `/afc:doctor` | Diagnose project health and plugin setup |\n| `/afc:architect` | Architecture analysis (persistent memory) |\n| `/afc:security` | Security scan (persistent memory, isolated worktree) |\n| `/afc:principles` | Project principles management |\n| `/afc:checkpoint` | Save session state |\n| `/afc:resume` | Restore session state |\n| `/afc:tasks` | Task decomposition (auto-generated by implement) |\n| `/afc:ideate` | Explore and structure a product idea |\n| `/afc:launch` | Generate release artifacts (changelog, tag, publish) |\n| `/afc:validate` | Verify artifact consistency |\n| `/afc:analyze` | General-purpose code and component analysis |\n| `/afc:qa` | Project quality audit — test confidence, error resilience, code health |\n| `/afc:consult` | Expert consultation (backend, infra, PM, design, marketing) |\n| `/afc:triage` | Analyze open PRs and issues in parallel |\n| `/afc:issue` | Analyze a single GitHub issue and create actionable document |\n| `/afc:resolve` | Analyze and address LLM bot review comments on a PR |\n| `/afc:pr-comment` | Generate structured PR review comments |\n| `/afc:release-notes` | Generate release notes from git history |\n| `/afc:learner` | Review and promote learned patterns to project rules |\n| `/afc:clarify` | Resolve spec ambiguities |\n\n### Individual Command Examples\n\n```bash\n# Write a spec for a specific feature\n/afc:spec \"Add dark mode toggle\"\n\n# Design a plan from an existing spec\n/afc:plan\n\n# Debug a specific error\n/afc:debug \"TypeError: Cannot read property 'user' of undefined\"\n\n# Run code review on current changes\n/afc:review\n\n# Explore and structure a product idea\n/afc:ideate \"real-time collaboration feature\"\n\n# Triage open PRs and issues\n/afc:triage              # all open PRs + issues\n/afc:triage --pr         # PRs only\n/afc:triage --deep       # deep analysis with diff review\n/afc:triage 42 99        # specific items by number\n```\n\n## Hook Events\n\nEvery hook fires automatically — no configuration needed after install.\n\n| Hook | What it does |\n|---|---|\n| `SessionStart` | Restores pipeline state on session resume |\n| `PreCompact` | Auto-checkpoints before context compression |\n| `PreToolUse` | Blocks dangerous commands (`push --force`, `reset --hard`) |\n| `PostToolUse` | Tracks file changes + auto-formats code |\n| `SubagentStart` | Injects pipeline context into subagents |\n| `Stop` | CI gate (shell) + code completeness check (shell) |\n| `SessionEnd` | Warns about unfinished pipeline |\n| `PostToolUseFailure` | Diagnostic hints for known error patterns |\n| `Notification` | Desktop alerts (macOS/Linux) |\n| `TaskCompleted` | CI gate (shell) + acceptance criteria verification (LLM) |\n| `SubagentStop` | Tracks subagent completion in pipeline log |\n| `UserPromptSubmit` | **Inactive**: detects intent keywords and suggests matching afc skill. **Active**: injects Phase/Feature context + drift checkpoint at threshold prompts |\n| `PermissionRequest` | Auto-allows CI commands during implement/review |\n| `ConfigChange` | Audits/blocks settings changes during active pipeline |\n| `TeammateIdle` | Prevents Agent Teams idle during implement/review |\n| `WorktreeCreate` | Sets up worktree isolation for parallel workers |\n| `WorktreeRemove` | Cleans up worktree after worker completion |\n\nHandler types: `command` (shell scripts, all events), `prompt` (LLM single-turn, TaskCompleted).\n\n## Persistent Memory Agents\n\n| Agent | Role |\n|---|---|\n| `afc-architect` | Remembers ADR decisions and architecture patterns across sessions. Auto-invoked during Plan (ADR recording) and Review (architecture compliance). |\n| `afc-security` | Remembers vulnerability patterns and false positives across sessions. Auto-invoked during Review (security scanning). Runs in isolated worktree. |\n| `afc-impl-worker` | Parallel implementation worker. Receives pre-assigned tasks from orchestrator. Ephemeral (no memory). Max 50 turns, auto-approve edits. |\n| `afc-pr-analyst` | PR deep analysis worker for triage. Runs in isolated worktree with diff access. Max 15 turns. |\n\n## Expert Consultation\n\nGet advice from domain specialists — each with persistent memory of your project:\n\n```bash\n/afc:consult backend \"Should I use JWT or session cookies?\"\n/afc:consult infra \"How should I set up CI/CD?\"\n/afc:consult pm \"How should I prioritize my backlog?\"\n/afc:consult design \"Is this form accessible?\"\n/afc:consult marketing \"How to improve SEO?\"\n/afc:consult legal \"Do I need GDPR compliance?\"\n/afc:consult security \"Is storing JWT in localStorage safe?\"\n/afc:consult advisor \"I need a database for my Next.js app\"\n\n# Auto-detect domain from question\n/afc:consult \"My API is slow when loading the dashboard\"\n\n# Exploratory mode — expert asks diagnostic questions\n/afc:consult backend\n```\n\n| Expert | Domain |\n|---|---|\n| `backend` | API design, database, authentication, server architecture |\n| `infra` | Deployment, CI/CD, cloud, monitoring, scaling |\n| `pm` | Product strategy, prioritization, user stories, metrics |\n| `design` | UI/UX, accessibility, components, user flows |\n| `marketing` | SEO, analytics, growth, content strategy |\n| `legal` | GDPR, privacy, licenses, compliance, terms of service |\n| `security` | Application security, OWASP, threat modeling, secure coding |\n| `advisor` | Technology/library/framework selection, ecosystem navigation |\n\nFeatures:\n- **Persistent memory**: experts remember your project's decisions across sessions\n- **Overengineering Guard**: recommendations scaled to your actual project size\n- **Domain adapters**: industry-specific guardrails (fintech, ecommerce, healthcare)\n- **Pipeline-aware**: when a pipeline is active, experts consider the current phase context\n\n## Task Orchestration\n\nThe implement phase automatically selects execution strategy:\n\n| Parallel tasks in phase | Mode |\n|---|---|\n| 0 | Sequential — one task at a time |\n| 1–5 | Parallel Batch — concurrent Task() calls |\n| 6+ | Swarm — orchestrator pre-assigns tasks to worker agents (max 5) |\n\nDependencies are tracked via DAG. CI gate + Mini-Review + Auto-Checkpoint run at each phase boundary.\n\n## Configuration\n\n```\n/afc:setup    # One-time: inject routing block into ~/.claude/CLAUDE.md\n/afc:init     # Per-project: detect stack and generate .claude/afc.config.md\n```\n\n- **`/afc:setup`** — Manages the AFC routing block in your global `~/.claude/CLAUDE.md`. Run once after install and again after plugin updates. Idempotent — skips if version matches.\n- **`/afc:init`** — Auto-detects your tech stack (package manager, framework, architecture, testing, linting) and generates project-local config files. No manual preset selection needed.\n\n## Development Docs\n\n| Document | Purpose |\n|----------|---------|\n| [Skill Authoring Guide](docs/skill-authoring-guide.md) | Rules for writing effective SKILL.md files |\n| [Agent Authoring Guide](docs/agent-authoring-guide.md) | Rules for writing effective AGENT.md files |\n| [Context Management Harness](docs/context-management-harness.md) | Context preservation, token efficiency, and compaction strategy |\n| [Orchestration Modes](docs/orchestration-modes.md) | Sequential, parallel batch, and swarm execution patterns |\n| [Critic Loop Rules](docs/critic-loop-rules.md) | Convergence-based quality verification protocol |\n| [Phase Gate Protocol](docs/phase-gate-protocol.md) | Phase transition validation |\n| [Expert Protocol](docs/expert-protocol.md) | Expert consultation agent behavioral rules |\n\n## FAQ\n\n### Does it work with any project?\nYes. Run `/afc:init` to auto-detect your stack. Works with JavaScript/TypeScript, Python, Rust, Go, and any project with a CI command.\n\n### Does it require any dependencies?\nNo. Pure markdown commands + bash hook scripts. No npm packages are imported at runtime.\n\n### What happens if CI fails during the pipeline?\nDebug-based RCA: traces the error, forms a hypothesis, applies a targeted fix. Halts after 3 failed attempts with full diagnosis.\n\n### Can I run individual phases?\nYes. Each phase has its own command (`/afc:spec`, `/afc:plan`, `/afc:implement`, `/afc:review`, `/afc:clean`). `/afc:auto` runs them all.\n\n### What are Critic Loops?\nConvergence-based quality checks after each phase. They evaluate output against criteria and auto-fix issues until stable. 4 verdicts: PASS, FAIL, ESCALATE (asks user), DEFER.\n\n### How many tokens does a pipeline run use?\nDepends on project size and feature complexity. A typical `/afc:auto` run for a medium feature uses roughly the same as a detailed manual implementation session — the pipeline adds structure, not overhead.\n\n### Can I customize the pipeline behavior?\nYes. Edit `.claude/afc.config.md` to change CI commands, architecture rules, and code style conventions. The pipeline reads this config at every phase.\n\n### Does it work with monorepos?\nYes. Run `/afc:init` in the monorepo root. The init command detects workspace structure and configures accordingly.\n\n### Can multiple team members use it on the same repo?\nYes. Each developer runs their own pipeline independently. The `.claude/afc.config.md` config is shared (commit it to the repo), but pipeline state is local and session-scoped.\n\n### How is this different from Cursor / Copilot / other AI tools?\nAll-for-claudecode is not a code completion tool — it is a structured development pipeline. It enforces spec → plan → implement → review flow with quality gates, persistent memory agents, and CI verification at every step.\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjhlee0409%2Fall-for-claudecode","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjhlee0409%2Fall-for-claudecode","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjhlee0409%2Fall-for-claudecode/lists"}