{"id":49496792,"url":"https://github.com/pcliangx/appgenesisforge","last_synced_at":"2026-05-30T11:00:30.518Z","repository":{"id":354324871,"uuid":"1223142852","full_name":"pcliangx/AppGenesisForge","owner":"pcliangx","description":"Production-ready AI Agent Team template for Claude Code — 14 specialists, Agile+Scrum+TDD enforced via skill/hook/DoD 3-layer (not wiki), PRD→UAT 6 stage gates, 4-layer hook defense, multi-LLM (DeepSeek/Doubao/Qwen/MiniMax), WeChat Mini Program, trilingual README (中文/EN/日本語). Ship a feature overnight.","archived":false,"fork":false,"pushed_at":"2026-05-25T07:16:49.000Z","size":65858,"stargazers_count":8,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-25T07:23:17.630Z","etag":null,"topics":["agent-team","agile-scrum","ai-agents","claude","claude-code","deepseek","doubao","fastapi","llm","minimax","multi-agent","prompt-engineering","python","qwen","rag","react","sub-agents","tdd","template","wechat-miniprogram"],"latest_commit_sha":null,"homepage":"","language":"Python","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/pcliangx.png","metadata":{"files":{"readme":"README.en.md","changelog":"CHANGELOG.md","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":"2026-04-28T03:36:39.000Z","updated_at":"2026-05-25T07:16:53.000Z","dependencies_parsed_at":"2026-05-04T13:00:39.333Z","dependency_job_id":"931a2360-8ba5-4b88-923b-3ed7c753f425","html_url":"https://github.com/pcliangx/AppGenesisForge","commit_stats":null,"previous_names":["pcliangx/appgenesisforge"],"tags_count":16,"template":true,"template_full_name":null,"purl":"pkg:github/pcliangx/AppGenesisForge","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pcliangx%2FAppGenesisForge","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pcliangx%2FAppGenesisForge/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pcliangx%2FAppGenesisForge/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pcliangx%2FAppGenesisForge/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pcliangx","download_url":"https://codeload.github.com/pcliangx/AppGenesisForge/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pcliangx%2FAppGenesisForge/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33689564,"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":"2026-05-30T02:00:06.278Z","response_time":92,"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":["agent-team","agile-scrum","ai-agents","claude","claude-code","deepseek","doubao","fastapi","llm","minimax","multi-agent","prompt-engineering","python","qwen","rag","react","sub-agents","tdd","template","wechat-miniprogram"],"created_at":"2026-05-01T10:01:19.920Z","updated_at":"2026-05-30T11:00:30.498Z","avatar_url":"https://github.com/pcliangx.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# App Genesis Forge · Your AI Coworker Team\n\n\u003e **Code the Origin, Forge the App.**\n\u003e 14 AI coworkers · Agile + Scrum + TDD backbone · ship a feature overnight · watch it all in one browser tab.\n\n[![GitHub Template](https://img.shields.io/badge/GitHub-Template-2ea44f?logo=github)](https://github.com/pcliangx/AppGenesisForge/generate)\n[![Release](https://img.shields.io/github/v/release/pcliangx/AppGenesisForge)](https://github.com/pcliangx/AppGenesisForge/releases)\n[![License: MIT](https://img.shields.io/badge/license-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Claude Code](https://img.shields.io/badge/Claude%20Code-%E2%89%A5%20v2.1.154-orange?logo=anthropic)](https://claude.com/claude-code)\n[![Methodology](https://img.shields.io/badge/methodology-Agile%20Scrum%20%2B%20TDD-9b59b6)](#-core-thinking-agile--scrum--tdd)\n[![Agents](https://img.shields.io/badge/agents-14-9b59b6?logo=robotframework\u0026logoColor=white)](.claude/agents/)\n[![Commands](https://img.shields.io/badge/commands-5-3498db)](.claude/commands/)\n[![Skills](https://img.shields.io/badge/skills-11-1abc9c)](.claude/skills/)\n[![LLM](https://img.shields.io/badge/LLM-DeepSeek%20%7C%20Doubao%20%7C%20Qwen%20%7C%20MiniMax-ff6b6b)](.claude/skills/agf-wiring-multi-llm-sdk/)\n[![WeChat](https://img.shields.io/badge/WeChat-MiniProgram-07c160?logo=wechat\u0026logoColor=white)](.claude/standards/miniapp.md)\n[![Hooks](https://img.shields.io/badge/hooks-4%20layers-2c3e50?logo=shieldsdotio\u0026logoColor=white)](.claude/standards/security.md)\n[![Stars](https://img.shields.io/github/stars/pcliangx/AppGenesisForge?style=social)](https://github.com/pcliangx/AppGenesisForge/stargazers)\n[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen)](https://github.com/pcliangx/AppGenesisForge/pulls)\n\n[简体中文](README.md) · **English**\n\n\u003e 📖 **Reading path (Setup → Detail → Wrap)**:\n\u003e - **Setup (conclusion first)** ── [💡 Conclusion](#-what-it-is-conclusion-first) → [🧠 Philosophy](#-core-thinking-agile--scrum--tdd)\n\u003e - **Detail (3 pillars + onboarding)** ── [🏢 Organization](#-organization--who) → [🔄 Process](#-process--how) → [⚙️ Mechanism](#-mechanism--enforcement) → [⏱ Day 1](#-day-1) → [🛠️ Tools](#-self-service)\n\u003e - **Wrap (closing)** ── [🔍 Comparison](#-vs-others) → [✨ Summary](#-summary)\n\n---\n\n## 💡 What It Is (Conclusion First)\n\n**AppGenesisForge** is an **AI team scaffold** on [Claude Code Agent Teams](https://code.claude.com/docs/en/agent-teams) — not a prompt collection, not a roster of agent personalities, but a **virtual AI team with Agile + Scrum + TDD backbone, defined workflow + standards, and acceptance gates**.\n\n### Core conclusion (one sentence)\n\n\u003e **Agile + Scrum + TDD principles are wired into the skill / hook / DoD enforcement path — never relying on agent self-discipline.**\n\n### 6 facts\n\n- **🧠 Methodology backbone is non-negotiable** — Agile + Scrum + TDD ([see §Philosophy](#-core-thinking-agile--scrum--tdd))\n- **🏢 Clear organization** — 14 AI coworkers with role contracts ([see §Organization](#-organization--who))\n- **🔄 Closed-loop process** — PRD → UAT 6 stage gates, no skipping on failure ([see §Process](#-process--how))\n- **🚀 Controllable parallelism** — Multi-instance Worker Pool ([ADR-001](docs/adr/001-multi-instance-worker-pool.md)): ≥2 same-type pending tasks → Dev / Reviewer / QA three-layer auto fan-out; PL fans-in with `agf-matrix.sh`\n- **⚙️ Mechanism backstop** — skill enforcement / hook block / DoD checklist, three layers ([see §Mechanism](#-mechanism--enforcement))\n- **🇨🇳 China-native ecosystem** — DeepSeek / Doubao / Qwen / MiniMax + WeChat Mini Program ([see §Tools](#-self-service))\n\n### Boundary\n\n✅ **Built for**: React + FastAPI + Postgres · AI Agent / RAG / multimodal · WeChat Mini Programs (native + Taro fallback) · full PRD → UAT loop\n\n❌ **Not built for**: native iOS / Android · desktop GUI · large-model training\n\n\u003e 📝 **Default backend is Python (FastAPI + SQLAlchemy + Alembic)**, frontend React + Vite, **extensible to Java / Go / Rust** and other backend stacks — OpenAI-compatible LLM wiring / Agile + Scrum + TDD principles / 4-layer hook defense / 14-coworker role contracts are all language-agnostic. To swap stacks, `tech-lead` rewrites [`ADR-000`](.claude/skills/agf-writing-adr/SKILL.md) + the Python examples in [`backend-dev`](.claude/agents/backend-dev.md) / [`testing.md`](.claude/standards/testing.md) / `agf-wiring-multi-llm-sdk`.\n\n---\n\n## 🧠 Core Thinking: Agile + Scrum + TDD\n\nAI agents have two natural weaknesses: **lost context + over-confidence**. Scrum stage gates + Agile iterative feedback + TDD red-green-refactor are the mature disciplines against both, and this project **lands them across three layers — Organization + Process + Mechanism**. This section covers WHAT/WHY; the next three cover HOW.\n\nFull decision log: [`product-workflow.md §4.4`](./docs/product-workflow.md#44-agile--scrum-心法采用清单--词汇替代) + [`team-capability-map.md §1.6`](./docs/team-capability-map.md#16-scrum-词汇--本项目载体feature-流变体).\n\n### Principles checklist (all mandatory / three-layer landing)\n\n| Agile / Scrum concept | Project carrier | Landing layer |\n|---|---|---|\n| **TDD red-green-refactor** | `superpowers:test-driven-development` + DoD order rule | ⚙️ Mechanism |\n| **AC (Acceptance Criteria)** | PRD §4 table (P0/P1) + dispatch must quote AC verbatim | 🔄 Process + ⚙️ Mechanism |\n| **DoD (Definition of Done)** | [`ac-lifecycle.md`](.claude/standards/ac-lifecycle.md) 9-item checklist | ⚙️ Mechanism |\n| **DoR (Definition of Ready)** | `brainstorming` done + AC verifiable in ≤30s + Open Q has Owner | 🔄 Process |\n| **User Story (INVEST)** | PRD §3 table + US↔AC ID cross-reference | 🔄 Process |\n| **Product Owner + Scrum Master** | `product-lead` (PO+SM merged) | 🏢 Organization |\n| **Dev Team (cross-functional)** | 5 dev + 1 Designer + 2 Reviewer + 2 QA + 2 Post-launch = 12 + PL/TL = 14 | 🏢 Organization |\n| **Sprint** | One feature = PRD → UAT signoff loop | 🔄 Process |\n| **Sprint Planning** | `superpowers:writing-plans` (async) | 🔄 Process |\n| **Daily Standup** | `progress/\u003crole\u003e.md` + SendMessage (async) | ⚙️ Mechanism |\n| **Sprint Review** | UAT business signoff | 🔄 Process |\n| **Sprint Retrospective** | `/agf-release-retro vX.Y.Z` (mandatory for MAJOR/MINOR) | 🔄 Process |\n\n### Scrum vocabulary → project carrier (substitution map)\n\n| Scrum term | Project substitute | Reason |\n|---|---|---|\n| **Sprint** (timed iteration) | Feature stream | Agent Team is continuously async; no sync cadence |\n| **Product Backlog** | `docs/prd/` files with Status=Draft/Review | File-based, git-trackable |\n| **Sprint Backlog** | `~/.claude/tasks/\u003cteam\u003e/*.json` | PL maintains via `TaskCreate/Update`; viewed via `/agf-tasks` |\n| **Story Points** | PRD `Estimated effort tier: S/M/L` | Tied to token budget tiers; more precise than abstract points |\n| **Velocity / Burndown** | Not tracked | No timed iterations → velocity meaningless; ≥3 retros later, cycle-time trend is evaluated (implicit form) |\n| **Daily Standup** | `progress/\u003crole\u003e.md` + SendMessage | Async standup + hook backstop |\n\n---\n\n## 🏢 Organization / WHO\n\n\u003e Scrum 3-role mapping + 14 AI coworkers. **Self-managed, cross-functional** — devs self-run Unit + SIT, Reviewers don't touch source, QA doesn't sign business off.\n\n### Scrum 3-role mapping\n\n| Scrum role | Project carrier | Notes |\n|---|---|---|\n| **Product Owner** | [`product-lead`](.claude/agents/product-lead.md) | PRD / priority P0/P1 / UAT business signoff |\n| **Scrum Master** | `product-lead` (PO+SM merged) | Workflow orchestration / skill enforcement / retro chairing. Agent has no human conflict of interest; merging is reasonable. |\n| **Development Team** | 12 execution / review / QA / post-launch roles (see below) | Self-managed; devs self-run Unit + SIT; ≥2 same-type pending tasks auto fan-out into a Pool ([ADR-001](docs/adr/001-multi-instance-worker-pool.md)) |\n| **Technical Advisor** (not a Scrum role) | [`tech-lead`](.claude/agents/tech-lead.md) | Only intervenes for missing baseline / new tech selection / architecture risk escalation |\n\n### The 14 AI coworkers\n\n| # | Coworker | Personality + responsibility |\n|---|---|---|\n| 🟠 001 | [`product-lead`](.claude/agents/product-lead.md) | **PO + SM** — never codes, only signs. PRD / task assignment / UAT signoff / retro chair |\n| 🔵 002 | [`tech-lead`](.claude/agents/tech-lead.md) | Battle-scarred veteran — no alternatives = no decision. Only enters for missing baseline / new tech selection / architecture risk |\n| 🟢 003 | [`frontend-dev`](.claude/agents/frontend-dev.md) | Components are contracts — React+Vite + Unit + SIT self-run |\n| 🟢 004 | [`backend-dev`](.claude/agents/backend-dev.md) | Schema migration PTSD — FastAPI / SQLAlchemy + Unit + SIT self-run |\n| 🟢 005 | [`ai-agent-dev`](.claude/agents/ai-agent-dev.md) | Prompts are code — LLM / RAG / Agent + Unit + SIT self-run |\n| 🟢 006 | [`ml-engineer`](.claude/agents/ml-engineer.md) | Quality-latency-cost triangle — multimodal inference + Unit + SIT self-run |\n| 🟢 007 | [`uiux-designer`](.claude/agents/uiux-designer.md) | spec.md + index.html dual delivery + AC coverage table |\n| 🟢 008 | [`miniapp-dev`](.claude/agents/miniapp-dev.md) | Native-first, Taro fallback — setData 256KB is the hard wall |\n| 🟡 009 | [`code-reviewer`](.claude/agents/code-reviewer.md) | Writes only to docs/reviews/ — code review + SIT Audit (4 checks + 3-tier verdict) |\n| 🟡 010 | [`miniapp-code-reviewer`](.claude/agents/miniapp-code-reviewer.md) | Zero tolerance for review red lines — wx.* + bundle size + privacy + SIT Audit |\n| 🔴 011 | [`qa-engineer`](.claude/agents/qa-engineer.md) | Default verdict ❌ — no curl/screenshot/DB diff = no Pass. E2E + UAT |\n| 🔴 012 | [`miniapp-qa-engineer`](.claude/agents/miniapp-qa-engineer.md) | E2E without real-device QR scan = no signoff |\n| 🟪 013 | [`content-writer`](.claude/agents/content-writer.md) | Numbers over adjectives, hook in first sentence — release notes / blog |\n| 🟪 014 | [`growth-analyst`](.claude/agents/growth-analyst.md) | Metrics before instinct — North Star / OMTM / A/B experiments |\n\nCapability baseline (model / tools / preloaded skills): [`team-roles.md`](.claude/standards/team-roles.md); end-to-end message flow: [`team-capability-map.md §2`](./docs/team-capability-map.md).\n\n---\n\n## 🔄 Process / HOW\n\n\u003e Full chain for a feature from requirement to delivery. **6 stage gates progress in order; no skipping on failure.**\n\n### End-to-end overview\n\n```mermaid\nflowchart LR\n    U([👤 User]) --\u003e S1[\"S1 Discovery\u003cbr/\u003ebrainstorming → PRD\"]\n    S1 --\u003e S2[\"S2 Dispatch\u003cbr/\u003e6-section schema + AC quote\"]\n    S2 --\u003e POOL{\"≥2 same-type\u003cbr/\u003epending tasks?\"}\n    POOL --\u003e|yes| FANOUT[\"⚙️ Pool fan-out\u003cbr/\u003espawn type-1 / type-2 / ...\u003cbr/\u003eADR-001\"]\n    POOL --\u003e|no| S3\n    FANOUT --\u003e S3[\"S3 TDD Implementation\u003cbr/\u003ered→green→refactor\u003cbr/\u003e+ Unit + SIT self-run\"]\n    S3 --\u003e FANIN[\"agf-matrix.sh\u003cbr/\u003ePL fan-in aggregation\u003cbr/\u003e(pool mode only)\"]\n    FANIN --\u003e S4[\"S4 Code Review\u003cbr/\u003e+ SIT Audit\u003cbr/\u003e3-tier verdict\"]\n    S4 --\u003e S5[\"S5 E2E\u003cbr/\u003echrome-devtools-mcp\u003cbr/\u003e3-tier verdict\"]\n    S5 --\u003e S6[\"S6 UAT\u003cbr/\u003eP0 case pass^2\u003cbr/\u003ePL business signoff\"]\n    S6 --\u003e D([🎁 Delivery])\n    S6 -.-\u003e|optional| POST[\"Post-Launch\u003cbr/\u003econtent + growth\"]\n\n    S4 -.block / Redo SIT.-\u003e S3\n    S5 -.Block.-\u003e S3\n    S6 -.request changes.-\u003e S3\n\n    style U fill:#3b82f6,color:#fff\n    style S6 fill:#f97316,color:#fff\n    style D fill:#22c55e,color:#fff\n    style FANOUT fill:#7c3aed,color:#fff\n    style FANIN fill:#7c3aed,color:#fff\n```\n\nFull diagram (with subgraphs + mini-program variant + post-launch chain + stage × Hook + stage × Skill + full Pool quick-reference): [`team-capability-map.md §1.1-§1.7`](./docs/team-capability-map.md).\n\n### One feature = one Sprint\n\n| Sprint stage | Who + what | Artifact |\n|---|---|---|\n| **Planning** | #001 `brainstorming` clarifies → PRD → `writing-plans` plan | `docs/prd/\u003cfeature\u003e-\u003cdate\u003e.md` (10 sections / AC P0/P1) |\n| **Design** | #007 spec.md + standalone HTML prototype + **AC coverage table** | `docs/design/\u003cfeature\u003e/{spec.md,index.html}` |\n| **TDD Implementation** | #003 + #004 parallel (separate worktrees) → red → green → refactor; **≥2 same-type pending tasks → auto fan-out into a Pool (instances named `\u003ctype\u003e-N`)** | code + `tests/sit/` |\n| **Async Standup** | After each Task → append `progress/\u003crole\u003e{-N}.md` (5 sections: state / Skills / SIT evidence [with AC `[x]/[ ]` inline] / quality gate / next step); in Pool mode PL fans-in with `agf-matrix.sh --type=progress` | `progress/*.md` |\n| **Code Review + SIT Audit** | #009 dual verdict (code `approve` / `approve with changes` / `block` + SIT Audit `Pass` / `Pass with concerns` / `Redo SIT`); Pool mode `-r\u003cN\u003e` | `docs/reviews/\u003cfeature\u003e(-r\u003cN\u003e)-\u003cdate\u003e.md` |\n| **Sprint Review (E2E + UAT)** | #011 runs E2E (verdict `Promote` / `Conditional promote` / `Block`) → UAT (**P0 case pass^2 / passes 2 times in a row** before business signoff `approve` / `request changes`); Pool mode `-e2e-q\u003cN\u003e` / `-uat-q\u003cN\u003e` | `docs/qa/\u003cfeature\u003e-{e2e,uat}(-q\u003cN\u003e)-\u003cdate\u003e.md` |\n| **Signoff + archive** | #001 business signoff → `archive-progress.sh` archives progress | `docs/qa/\u003cfeature\u003e-process-log.md` |\n| **Retrospective** (MAJOR/MINOR) | #001 `/agf-release-retro vX.Y.Z` (7 steps + §5 Owner+Due mandatory) | `docs/reviews/retro-vX.Y.Z-\u003cdate\u003e.md` |\n\n### PRD → Task decomposition rules\n\nSee [`product-workflow.md §3.3`](./docs/product-workflow.md#33-拆分规则硬性条款):\n\n- 1 User Story = 1~N Tasks, **split by role boundary** (FE/BE/AI/ML), not by AC; each Task has ≥1 AC, quoted verbatim in SendMessage\n- Task granularity = closed-loop within one session (implement + Unit + AC self-check)\n- AC is a leaf, not splittable — if too large, split its \"observable outcome\"\n\n### Failure loop (any stage fail → no skipping, return to S3)\n\n\u003e **4 verdict vocabularies** (team convention, no improvisation; see [`workflow.md §Verdict 词表`](.claude/standards/workflow.md)): code review `approve` / `approve with changes` / `block` · SIT Audit `Pass` / `Pass with concerns` / `Redo SIT` · QA report-level `Promote` / `Conditional promote` / `Block` · UAT business signoff `approve` / `request changes`.\n\n| Stage gate | Failure verdict | Failure action | Returns to |\n|---|---|---|---|\n| **Code Review** | `block` | PL re-dispatches execution layer to fix | S3 |\n| **SIT Audit** | `Redo SIT` | PL combines re-dispatch (with code fix) | S3 (does not progress to E2E) |\n| **E2E** | `Block` / `Conditional promote` | qa reports → PL re-dispatches | S3 (does not progress to UAT) |\n| **UAT business signoff** | `request changes` | PL re-dispatches | S3 |\n| **P0 case pass^2** | fails to pass twice in a row | qa withholds signoff, returns to S3 ([`agf-writing-qa-report`](.claude/skills/agf-writing-qa-report/) enforced) | S3 |\n| **Pool single-instance fail** | a single `-N` instance is blocked | PL respawns that instance (other instances keep running) | local rollback of that `-N` |\n| **Pool ≥50% fail** | widespread failure | PL aborts the whole batch + PRD review | S1 |\n\n**code-reviewer / qa-engineer never touch source directly.**\n\n---\n\n## ⚙️ Mechanism / ENFORCEMENT\n\n\u003e Agile + Scrum + TDD principles are **wired into skill / hook / DoD three-layer enforcement** — never relying on agent self-discipline.\n\n### TDD enforcement chain\n\n```mermaid\nflowchart LR\n    PL([🟠 PL dispatches\u003cbr/\u003enew feature / bugfix]) --\u003e HOOK[\"validate-task-schema\u003cbr/\u003e6 sections complete\"]\n    HOOK --\u003e SKILL[\"invoke skill\u003cbr/\u003etest-driven-development\"]\n    SKILL --\u003e RED[\"🔴 red\u003cbr/\u003ewrite failing test\u003cbr/\u003ecommit: test:\"]\n    RED --\u003e GREEN[\"🟢 green\u003cbr/\u003eminimal impl turns test green\u003cbr/\u003ecommit: feat: / fix:\"]\n    GREEN --\u003e REFACTOR[\"🔵 refactor\u003cbr/\u003etidy code, keep green\u003cbr/\u003ecommit: refactor:\"]\n    REFACTOR --\u003e PR[\"PR commit history\u003cbr/\u003efirst test before first impl\"]\n    PR --\u003e CR[\"code-reviewer\u003cbr/\u003eorder check\"]\n    CR --\u003e PASS([✅ Proceed to\u003cbr/\u003ecode review + SIT Audit])\n\n    REFACTOR -.iterate.-\u003e RED\n    CR -.violation = block.-\u003e RED\n\n    style PL fill:#f97316,color:#fff\n    style PASS fill:#22c55e,color:#fff\n```\n\n**Skip condition**: pure refactor / docs / config tasks can skip TDD order ([`ac-lifecycle.md` DoD line 81–85](.claude/standards/ac-lifecycle.md)).\n\n### 4-layer Hook defense (red lines + reminders)\n\n| Layer | Trigger | Action |\n|---|---|---|\n| 🚫 | Dangerous commands: `rm -rf` / `DROP TABLE` / `git push --force` / `git reset --hard` | Hard block |\n| 🚫 | Secret leaks: 10 vendor tokens + PEM/SSH/PuTTY/BIP39 mnemonics | Hard block |\n| 🚫 | Prompt-injection in external content | Soft warning |\n| 🚫 | commit-time staged-diff secret scan | Hard block (Edit/Write bypass backstop) |\n| 💡 | Teammate wants idle but task list has pending | Reminder to stay and finish |\n| 💡 | Execution layer exits without writing `progress/\u003crole\u003e.md` | Block (**Daily Standup backstop**) |\n| 💡 | `TaskCreate` 6-section schema incomplete | Block (**AC quote enforcement**) |\n| 💡 | Pre-work skill check | Reminder (if not invoked) |\n\n### Stage × Hook × Skill triggers (merged view)\n\n| Stage | Hook (🛑 hard block / ⚠️ soft warning) | Skill (mandatory / recommended) |\n|---|---|---|\n| **prompt submit** | 🛑 `scan-secrets` (10 vendor secrets + PEM/SSH/PuTTY/BIP39)\u003cbr/\u003e⚠️ `skill-suggester` | — |\n| **S1 discovery + PRD** | — | `brainstorming` (mandatory if vague/multi-option)\u003cbr/\u003e`agf-writing-prd` |\n| **S2 dispatch** | 🛑 `validate-task-schema` (6 sections + AC quote) | `writing-plans` (≥3 AC / cross-role)\u003cbr/\u003e`using-git-worktrees` (≥2 dev parallel mandatory)\u003cbr/\u003e**Pool fan-out** (≥2 same-type pending tasks / [ADR-001](docs/adr/001-multi-instance-worker-pool.md)) |\n| **S3 implementation tool use** | 🛑 `block-dangerous-bash`\u003cbr/\u003e　Bash: `rm -rf` / `DROP TABLE` / `push --force` / `reset --hard`\u003cbr/\u003e⚠️ `sanitize-tool-output`\u003cbr/\u003e　WebFetch/WebSearch/Read/Bash/mcp__* output prompt-injection warning | `test-driven-development` mandatory (new feature/bugfix)\u003cbr/\u003e`agf-running-sit-tests` (after Unit)\u003cbr/\u003e`systematic-debugging` (on bug)\u003cbr/\u003e`verification-before-completion` (before report) |\n| **S3 exit/idle** | 🛑 `check-progress-file` (no progress entry → block)\u003cbr/\u003e🛑 `teammate-keepalive` (idle while pending → block) | — |\n| **git commit** | 🛑 `scan-commit` (staged diff same secret regex) | — |\n| **S4 review** | — | `requesting-code-review` (before trigger)\u003cbr/\u003e`receiving-code-review` (when bounced back) |\n| **S5/S6 testing** | — | `agf-writing-qa-report` (E2E/UAT report) |\n| **post-release**\u003cbr/\u003e(MAJOR/MINOR) | — | `agf-running-release-retro` (PATCH auto-aborts) |\n\n### Release discipline + No Equivalent Bypass\n\n**Release discipline**: MAJOR/MINOR must be tagged in the same session + tag annotation lists tagged-along commits + **must** run `/agf-release-retro`. See [`versioning.md`](.claude/standards/versioning.md).\n\n**Hard block hit** → **No Equivalent Bypass** (must not find equivalent workaround; must SendMessage PL and wait for authorization). See [`security.md`](.claude/standards/security.md).\n\n### 📖 Glossary\n\n**Collaboration actions** (frequent at runtime, see [`product-workflow.md §4.5`](./docs/product-workflow.md#45-协作动作collaboration-actions)):\n\n| Term | Meaning |\n|---|---|\n| **dispatch** | PL assigns Task to execution layer via SendMessage (6 sections + AC quote) |\n| **fan-out / fan-in** | Pool mode: ≥2 same-type pending tasks → PL spawns `\u003ctype\u003e-1` / `\u003ctype\u003e-2` ... (fan-out) → PL aggregates the multiple reports with `agf-matrix.sh --type=progress\\|review\\|qa` (fan-in) |\n| **pass^2** | At UAT, P0 cases must pass 2 times in a row before business signoff ([`agf-writing-qa-report`](.claude/skills/agf-writing-qa-report/) enforced) |\n| **escalate** | Request upper decision (exec→PL→user; reviewer→tech-lead for architecture risk) |\n| **halt / STOP ⛔** | Hook block / test fail / spec drift triggers; stop and SendMessage report — never bypass |\n| **verify-before-assert** | Must actually run verification before claiming \"done\"; no empty assertions |\n| **push back** | After review feedback, refuse with measured evidence |\n| **ghost mailbox** | Dispatching to nonexistent or destroyed mailbox |\n| **spec drift** | Document/PRD/spec contract diverges from actual code or database |\n| **sweep** | PL actively scans git log + task list + mailbox |\n| **mock-first** | Frontend implements UI with mock data, swaps to real endpoint when backend ready |\n\n**Status indicators** (team convention, no improvisation):\n\n| Symbol | Meaning | Typical location |\n|---|---|---|\n| ✅ | Done / passed | AC self-check, Code Review verdict, UAT signoff |\n| ⚠️ | Warning / deviation | AC self-check has gap, Code Review Warning |\n| ❌ | Failed / not passed | Test failure, Code Review request changes |\n| 🔄 | In progress | Task status, long-running progress |\n| ⏸ | Paused / pending | Waiting on external dep / clarification |\n| 💤 | idle / standby | Teammate on standby |\n| ⛔ | STOP / halt | Emergency stop (hook block / spec drift / test fail) |\n\n---\n\n## ⏱ Day 1\n\n**Prerequisite**: Claude Code ≥ v2.1.154 + Agent Teams enabled (`init-team.sh` validates).\n\n```bash\n# Scaffold a new project\ngh repo create my-app --template pcliangx/AppGenesisForge --private\ncd my-app \u0026\u0026 bash init-team.sh\n\n# Embed into existing repo (one-shot migration; never overwrites your CLAUDE.md / ADR-000 / settings.json)\nbash install-to-existing.sh ~/path/to/your-existing-repo\n\n# Try it\n/agf-team-start \u003cyour first feature\u003e\n```\n\nFull Day-1 checklist + prerequisites + pitfalls: [`docs/FIRST_RUN.md`](./docs/FIRST_RUN.md). ⚠️ Don't copy this repo's `CLAUDE.md` — the scaffold ships `CLAUDE.example.md`.\n\n---\n\n## 🛠️ Self-Service\n\n### Slash Commands (5, Scrum ceremony entries)\n\n| Command | Scrum ceremony |\n|---|---|\n| [`/agf-team-start`](.claude/commands/agf-team-start.md) | Sprint kickoff |\n| [`/agf-uat`](.claude/commands/agf-uat.md) | Sprint Review (business signoff) |\n| [`/agf-team-stop`](.claude/commands/agf-team-stop.md) | Sprint wrap-up (close execution-layer teammates after UAT) |\n| [`/agf-release-retro`](.claude/commands/agf-release-retro.md) | Sprint Retrospective (PATCH auto-aborts) |\n| [`/agf-tasks`](.claude/commands/agf-tasks.md) | Sprint Backlog view |\n\n### Skills (9 project-level + 2 third-party docx/pptx + superpowers suite)\n\n| Skill | Who / when |\n|---|---|\n| [`agf-writing-prd`](.claude/skills/agf-writing-prd/) | #001 writing PRD (10 sections + 5 AC rules + completion checklist) |\n| [`agf-writing-adr`](.claude/skills/agf-writing-adr/) | #002 recording architecture decisions (alternatives mandatory + version verification) |\n| [`agf-wiring-multi-llm-sdk`](.claude/skills/agf-wiring-multi-llm-sdk/) | #005 integrating DeepSeek/Doubao/Qwen/MiniMax |\n| [`agf-running-sit-tests`](.claude/skills/agf-running-sit-tests/) | Execution-layer devs self-running SIT |\n| [`agf-writing-qa-report`](.claude/skills/agf-writing-qa-report/) | #011 writing E2E/UAT reports |\n| [`agf-running-release-retro`](.claude/skills/agf-running-release-retro/) | #001 running MAJOR/MINOR retros |\n| [`agf-writing-docx-reports`](.claude/skills/agf-writing-docx-reports/) | Programmatic Chinese .docx reports (resolutions / reviews / RFPs) |\n| [`agf-writing-pptx-reports`](.claude/skills/agf-writing-pptx-reports/) | Programmatic Chinese .pptx decks (policy / public-sector / training) |\n| [`agf-writing-github-issue`](.claude/skills/agf-writing-github-issue/) | File issues in the repo (QA auto-path + locked labels) |\n\n**Superpowers suite** (everyone can invoke): `brainstorming` / `writing-plans` / `test-driven-development` / `systematic-debugging` / `verification-before-completion` / `requesting-code-review` / `receiving-code-review` / `using-git-worktrees` — enforcement points see [`superpowers.md`](.claude/standards/superpowers.md).\n\n### Scripts (4 PL/maintainer tools)\n\n| Script | Who / when |\n|---|---|\n| [`agf-tasks.sh`](.claude/scripts/agf-tasks.sh) | PL views the task-list table (invoked internally by slash `/agf-tasks`) |\n| [`agf-matrix.sh`](.claude/scripts/agf-matrix.sh) | PL Pool fan-in aggregation: `--type=progress\\|review\\|qa` three modes, merging N `\u003crole\u003e-N.md` / `-r\u003cN\u003e` / `-q\u003cN\u003e` reports into one table |\n| [`archive-progress.sh`](.claude/scripts/archive-progress.sh) | PL archives `progress/\u003crole\u003e{-N}.md` → `docs/qa/\u003cfeature\u003e-process-log.md` after UAT signoff (supports pool multi-instance merge) |\n| [`lint-all.sh`](.claude/scripts/lint-all.sh) | Repo-wide bash/JSON/YAML lint entry; chained by the pre-commit hook |\n\n---\n\n## 🔍 vs Others\n\n|  | **AppGenesisForge** | Generic prompt lib | Role-persona lib | Single-agent toolchain |\n|---|---|---|---|---|\n| **Methodology backbone** | ✅ Agile + Scrum + TDD (Organization / Process / Mechanism three layers) | ❌ | ❌ | ❌ |\n| **Organization** | ✅ 14 coworkers + Scrum role mapping | ❌ | ⚠️ role list only | ❌ |\n| **Process** | ✅ PL + 6 stage gates | ❌ | ⚠️ examples only | ❌ |\n| **Mechanism (TDD enforcement)** | ✅ commit order + skill + DoD | ❌ | ❌ | ❌ |\n| **Mechanism (Hook defense)** | ✅ 4 layers | ❌ | ❌ | ❌ |\n| **Retrospective** | ✅ 7 steps + Owner+Due mandatory | ❌ | ❌ | ❌ || **Downstream migration** | ✅ install-to-existing | ✅ copy-paste | ⚠️ fork | ⚠️ |\n| **China LLMs** | ✅ DeepSeek/Doubao/Qwen/MiniMax | ❌ | ❌ | depends |\n\n---\n\n## ✨ Summary\n\n- **What it is**: 14 AI coworkers + Agile + Scrum + TDD workflow + 4-layer hook defense\n- **What's unique**: Agile + Scrum + TDD principles **wired into Organization + Process + Mechanism three-layer landing**, never relying on agent self-discipline\n- **How to use**: `/agf-team-start \u003cfeature\u003e` → 14 coworkers run the Sprint flow → watch in one tab\n- **Your benefit**: ship a feature overnight; artifacts are traceable; stage-gate skipping = failure of duty\n\n\u003e **Core trade-off**: *Wire Agile + Scrum + TDD into the enforcement path, not a wiki* — the system's most important design choice. Rules forged from real iteration: early on PL raced to write code, Reviewer out-aggressed Dev, QA delivered no evidence — every hook, standard, and skill comes from a real stumble.\n\n### 🚀 Next Steps\n\n| You want to | How |\n|---|---|\n| **Try a fresh project** | `gh repo create --template pcliangx/AppGenesisForge` → [⏱ Day 1](#-day-1) |\n| **Embed into existing repo** | `bash install-to-existing.sh ~/your-repo` (never overwrites your `CLAUDE.md`/`ADR-000`/`settings.json`) |\n| **Install via Plugin** (lightest) | `/plugin marketplace add pcliangx/AppGenesisForge` → `/plugin install agf` → follow [`agf-plugin/POST_INSTALL.md`](agf-plugin/POST_INSTALL.md) to add required settings + external deps |\n| **See a real feature with full artifacts** | `ls docs/training/samples/postcard-feature/` — PRD → ADR → Dispatch → Progress → Review → UAT → Retro → Release notes (illustrative training paths) |\n| **Give feedback / open PR** | [🐛 Issue](https://github.com/pcliangx/AppGenesisForge/issues) · [🍴 PR](https://github.com/pcliangx/AppGenesisForge/pulls) |\n| **See what changed each release** | [📒 CHANGELOG](CHANGELOG.md) |\n\n### 📂 What's Included\n\n```text\n.claude/                14 agents · 17 standards · 11 skills · 12 hooks · 5 commands · 4 scripts · 2 rules\ndocs/                   product-workflow / team-capability-map / PRD·QA·ADR·Review·Retro templates\ndocs/training/samples/ · evals/      end-to-end worked example (postcard-feature) + per-role baseline JSONL\nprogress/               execution-layer Self-Reporting drafts (Async Daily Standup)init-team.sh            Day-1 health check (10 checks + auto pre-commit install)\ninstall-to-existing.sh  one-shot migration into existing repo\nCLAUDE.example.md       project-level CLAUDE.md template (don't confuse with this repo's CLAUDE.md)\n```\n\n### 🗺️ Roadmap\n\n**Done**:\n\n| Release | Content |\n|---|---|\n| Foundation | 4 China-domestic LLMs · WeChat MiniProgram trio · 4-layer hook defense · Self-Reporting Pattern · agent namespace steady state |\n| **v1.6.0** | team-dashboard zero-invasion + `install-to-existing.sh` one-shot migration |\n| **v1.7.0** | code-reviewer adopts `/simplify` Phase 1+2 review |\n| **v2.0.0** | H3 late-stage workflow: SIT ownership dev → code-reviewer audit |\n| **v3.0.0** | Removed cost audit feature (twice-empty = wrong discipline) |\n| **v3.1.0** | **Agile + Scrum + TDD enforcement complete** (skill / hook / DoD three-layer) + README rewrite + docs traceability |\n| **v3.1.1** | README Setup-Detail-Wrap restructure + Claude Code minimum version bumped to v2.1.130 |\n| **v3.2.0** | **Multi-instance Worker Pool ([ADR-001](docs/adr/001-multi-instance-worker-pool.md))**: Dev / Reviewer / QA three-layer pool; `agf-matrix.sh` three-mode fan-in; P0 case pass^2; 4 verdict vocabularies unified |\n\n**Up next**:\n\n- [ ] More skills: test cases / commit messages / release notes\n- [ ] More eval baselines: remaining role JSONL coverage\n- [ ] CI/CD: wire `init-team.sh` into GitHub Actions\n- [ ] feature cycle time trend visualization (enabled after ≥3 retros)\n\n---\n\n## 📜 License \u0026 Acknowledgments\n\nMIT — free for commercial use. Structural inspiration from [The Agency](https://github.com/msitarzewski/agency-agents).\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n**14 AI coworkers · Agile + Scrum + TDD (Organization / Process / Mechanism three-layer landing) · ship a feature overnight**\n\n[⭐ Star](https://github.com/pcliangx/AppGenesisForge) · [🍴 Fork](https://github.com/pcliangx/AppGenesisForge/fork) · [🐛 Issue](https://github.com/pcliangx/AppGenesisForge/issues) · [📒 CHANGELOG](CHANGELOG.md) · [🇨🇳 简体中文](README.md)\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpcliangx%2Fappgenesisforge","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpcliangx%2Fappgenesisforge","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpcliangx%2Fappgenesisforge/lists"}