Skip to content
Back to search

my-claude-devteam

MarketplaceWorks with Claude CodeGitHub

An engineering team in a box for Claude Code — 12 specialized agents, 15 automation hooks, and the P7/P9/P10 methodology.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/nycu-chung--my-claude-devteam/badge.svg)](/listings/nycu-chung--my-claude-devteam)

HTML

<a href="/listings/nycu-chung--my-claude-devteam"><img src="/api/listings/nycu-chung--my-claude-devteam/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

/plugin marketplace add NYCU-Chung/my-claude-devteam
/plugin install devteam@my-claude-devteam

Once installed, all 12 agents and 15 hooks register automatically. Restart Claude Code and your dev team is online.

Optional: install the methodology document

The plugin ships with the **P7/P9/P10 methodology + three red lines** baked into each agent, but for the strongest effect, also drop one of the `CLAUDE.md` files into `~/.claude/CLAUDE.md` so the whole session operates under the same discipline:

# English
curl -sL https://raw.githubusercontent.com/NYCU-Chung/my-claude-devteam/main/CLAUDE.en.md   -o ~/.claude/CLAUDE.md

# Traditional Chinese
curl -sL https://raw.githubusercontent.com/NYCU-Chung/my-claude-devteam/main/CLAUDE.zh-TW.md   -o ~/.claude/CLAUDE.md

Manual install (without plugin)

If you prefer not to use the plugin system:

git clone https://github.com/NYCU-Chung/my-claude-devteam ~/my-claude-devteam

mv ~/.claude/agents ~/.claude/agents.bak 2>/dev/null
mv ~/.claude/hooks  ~/.claude/hooks.bak  2>/dev/null

cp -r ~/my-claude-devteam/agents ~/.claude/
cp -r ~/my-claude-devteam/hooks  ~/.claude/
cp ~/my-claude-devteam/settings.example.json ~/.claude/settings.json
# (optional) cp ~/my-claude-devteam/CLAUDE.en.md ~/.claude/CLAUDE.md

**Verify the install:**

You: "I need to add a POST endpoint for broadcast messages"
Claude: [spawns fullstack-engineer with P7 methodology]
        [designs → implements → three-question self-review]
        [spawns critic for pre-deploy review]

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 22 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "my-claude-devteam",
  3. "owner": {
  4. "name": "NYCU-Chung",
  5. "url": "https://github.com/NYCU-Chung"
  6. },
  7. "metadata": {
  8. "description": "Claude Code Dev Team — 12 specialized subagents + 15 automation hooks + P7/P9/P10 methodology."
  9. },
  10. "plugins": [
  11. {
  12. "name": "devteam",
  13. "description": "An engineering team in a box. Installs 12 subagents and 15 hooks in one command. Includes the P7/P9/P10 methodology and three red lines discipline.",
  14. "version": "1.1.0",
  15. "source": "./",
  16. "author": {
  17. "name": "NYCU-Chung",
  18. "url": "https://github.com/NYCU-Chung"
  19. }
  20. }
  21. ]
  22. }
README.md · README · 240 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Claude Code Dev Team
  2. **English · [繁體中文](./README.zh-TW.md)**
  3. > **An entire engineering team for Claude Code**
  4. > — 12 specialized agents, 15 automation hooks, and the P7/P9/P10 methodology that keeps them disciplined.
  5. Most people use Claude Code as a single coder. This config turns it into a full engineering org: **planner, fullstack-engineer, refactor-specialist, migration-engineer, frontend-designer, critic, vuln-verifier, debugger, db-expert, onboarder, tool-expert, web-researcher** — each agent owns a role, each has its own tool permissions, and a strict delegation rulebook decides who touches what.
  6. Backed by **corporate-culture-inspired discipline** (closure, fact-driven, exhaustiveness) and **battle-tested hooks** that catch debugger statements, hardcoded secrets, cost overruns, and MCP outages before they hit main.
  7. ---
  8. ## The Team
  9. | Role | Agent | What they do | When they ship |
  10. |------|-------|--------------|---------------|
  11. | 📋 **Tech Lead** | `planner` | Breaks down fuzzy requirements into parallelizable Task Prompts with a six-element contract (goal / scope / input / output / acceptance / boundaries). Never writes code. | Task touches 3+ files or 2+ modules |
  12. | 🛠 **Senior Engineer** | `fullstack-engineer` | Ships features using the P7 methodology: read reality → design solution → impact analysis → implement → three-question self-review → `[P7-COMPLETION]` delivery. | Single-feature or cross-module implementation |
  13. | 🔄 **Refactor Lead** | `refactor-specialist` | Large-scale safe refactors. Atomic commits, full callsite verification, single-revert rollback. | Renames, file moves, module extraction across 10+ files |
  14. | 🚀 **Migration Lead** | `migration-engineer` | Framework / library major-version upgrades. Reads upstream changelog, executes incrementally, verifies at every step. | Next.js 13→14, Vue 2→3, Tailwind 3→4, etc. |
  15. | 🎨 **Designer** | `frontend-designer` | Builds landing pages, dashboards, and UI that doesn't look like AI slop. Opinionated aesthetic direction, refuses generic output. | New pages, UI redesigns, visual upgrades |
  16. | 🔍 **Code Reviewer** | `critic` | Finds bugs, security holes, logic errors, edge cases, performance issues. Every finding with file path + line number. No "looks good to me". | Pre-commit, pre-deploy, pre-merge |
  17. | 🧪 **Pentester** | `vuln-verifier` | Takes the critic's findings and writes actual PoC tests to prove the vulnerability is real — no false positives, no hand-waving. | After critic flags a security issue |
  18. | 🐛 **Debug Engineer** | `debugger` | Reads logs, constructs hypotheses, verifies, fixes. Never guesses, always traces root cause. Includes log-analyzer. | Bug reports, service incidents, test failures |
  19. | 🗄 **DB Specialist** | `db-expert` | Reviews schemas, migrations, queries for safety, indexes, locks, race conditions. Paranoid about data loss. | Schema changes, migrations, query optimization |
  20. | 🗺 **Onboarder** | `onboarder` | First-time codebase exploration. Produces a structured mental model — architecture, entry points, suspicious areas. | Joining a new project, evaluating an open-source repo |
  21. | ⚙️ **Tool Expert** | `tool-expert` | Picks the right MCP tools, chains complex workflows, troubleshoots tool failures. Knows every integration in your stack. | MCP tool failures, complex tool chaining |
  22. | 📚 **Researcher** | `web-researcher` | Fetches and synthesizes official docs, API specs, error code meanings. The antidote to hallucination. | Uncertain API usage, error code lookups |
  23. Each agent is a markdown file under `agents/` with its own system prompt, tool permissions, and model selection. **Customize them. Fork them. Replace the ones you don't need.**
  24. ---
  25. ## The Workflow
  26. ```
  27. ┌─────────────┐
  28. │ Your Task │
  29. └──────┬──────┘
  30. │
  31. ┌────────▼────────┐
  32. │ 📋 planner │ ← Breaks into parallel subtasks
  33. │ (Tech Lead) │ if touches 3+ files
  34. └────────┬────────┘
  35. │
  36. ┌─────────┼─────────┐
  37. ▼ ▼ ▼
  38. ┌─────────┐ ┌─────────┐ ┌─────────┐
  39. │ fullstk │ │ fullstk │ │ fullstk │ ← Parallel execution
  40. │ × N │ │ × N │ │ × N │ P7 methodology
  41. └────┬────┘ └────┬────┘ └────┬────┘
  42. └───────────┼───────────┘
  43. ▼
  44. ┌──────────────┐
  45. │ 🔍 critic │ ← Mandatory pre-deploy review
  46. │ (reviewer) │
  47. └───────┬──────┘
  48. │
  49. ┌────────┴────────┐
  50. │ │
  51. ▼ ▼
  52. ┌──────────────┐ ┌─────────────┐
  53. │ 🐛 debugger │ │ Deploy │
  54. │ (if issues) │ │ │
  55. └──────────────┘ └─────────────┘
  56. ```
  57. **Security-sensitive work** takes a detour: `critic` flags → `vuln-verifier` writes PoC → fix or file PR.
  58. ---
  59. ## The Methodology
  60. ### Three Red Lines
  61. Every agent enforces these. No exceptions. No "close enough".
  62. - **🔒 Closure Discipline** — Every task has a clear Definition of Done. "This is probably enough" is not an ending.
  63. - **📎 Fact-Driven** — Every judgment must cite actual code with paths and line numbers. "I guess" / "probably" / "should be" are violations.
  64. - **✅ Exhaustiveness** — Checklists cannot be skipped. Clean items must be explicitly marked "checked, no problems" — never silently ignored.
  65. ### P7/P9/P10 Mode Switching
  66. Not role-play. **Operating modes** that Claude switches between based on task scope:
  67. | Scope | Mode | Behavior |
  68. |-------|------|----------|
  69. | Single feature | **P7** (Senior Engineer) | Design → Impact analysis → Implement → Three-question self-review → `[P7-COMPLETION]` |
  70. | Multi-module, 3+ files | **P9** (Tech Lead) | Decompose into Task Prompts with six elements. Coding is forbidden — your output is prompts, not code. |
  71. | Cross-team, 5+ sprints | **P10** (CTO) | Output strategy docs. Goals, success metrics, risks, timeline, resource allocation. |
  72. ### PUA Mode (High-Pressure Triggers)
  73. The team shifts into exhaustive mode when:
  74. - Same task failed 2+ times → write three new hypotheses, no retrying the old one
  75. - About to say "I can't solve this" → forbidden, check docs and source
  76. - Being passive, waiting for instructions → find the next step yourself
  77. - User says "try harder" / "why did it fail again" → enter reflection mode
  78. - User says "don't get slapped again" → cross-verify every assumption 3 different ways
  79. > We don't keep idle agents. No half-finished work. No excuses.
  80. ---
  81. ## The Automation (Hooks)
  82. Fifteen automation hooks wire up at `pre-commit`, `post-tool-use`, and `stop` events. They catch problems before they ship.
  83. | Hook | Trigger | What it catches |
  84. |------|---------|-----------------|
  85. | 💰 `cost-tracker.js` | After every response | Token usage + estimated cost per model (Opus / Sonnet / Haiku). Running tally in `~/.claude/stats-cache.json` |
  86. | ✋ `commit-quality.js` | Pre-commit | Blocks commits with `debugger` statements or hardcoded secrets in JS/TS/Python files |
  87. | 🔧 `mcp-health.js` | MCP tool failures | Detects MCP server outages and suggests restart paths |
  88. | 🛡 `config-protection.js` | Edit/Write to critical files | Guards important config files from accidental overwrites |
  89. | 🎨 `design-quality.js` | Frontend changes | Checks for AI-slop indicators in UI code |
  90. | 📝 `check-console.js` | Pre-commit | Flags stray `console.log` in production paths |
  91. | 📊 `audit-log.js` | All tool calls | Keeps an audit trail of significant tool operations |
  92. | 🎯 `batch-format.js` | Multi-file edits | Runs formatter on modified files in batch |
  93. | 💡 `suggest-compact.js` | Context pressure | Suggests `/compact` when context window fills up |
  94. | 📈 `accumulator.js` | Session tracking | Accumulates session metrics |
  95. | 🚨 `log-error.sh` | Any error | Unified error logging to `~/.claude/error-log.md` |
  96. | 🧪 `test-runner.js` | After file edit | Finds sibling test file, runs vitest/jest, reports failures (non-blocking) |
  97. | 🔒 `branch-protection.js` | Pre-Bash | Hard-blocks force pushes and direct commits to main / master / production / release |
  98. | 📏 `large-file-warner.js` | Pre-Read | Warns at 500 KB, blocks at 2 MB to protect context window |
  99. | 📚 `session-summary.js` | Stop | Appends session summary to `~/.claude/sessions/` for later search |
  100. Each hook is a self-contained script. Enable / disable / customize in `settings.example.json`.
  101. ---
  102. ## From the Field
  103. Real observations from daily use. Your mileage may vary.
  104. ### `critic` is the MVP
  105. On mid-sized modules (500–2000 lines), `critic` routinely finds **20–30 issues** across all severity tiers. On large open-source codebases (tested against OpenClaw 352K⭐, Mermaid 87K⭐, Storybook 85K⭐, React Router 56K⭐), a single focused audit still surfaces **5–10 real bugs** that had not been reported in the issue tracker.
  106. Notable catches from real audits:
  107. - A CWE-208 timing-safe comparison gap in a 352K-star repo that **three prior security-hardening PRs had missed** (diffs store `!==` vs `safeEqualSecret`)
  108. - A non-atomic `writeFileSync` race in an auth-adjacent allowlist file that would corrupt state under concurrent access
  109. - An Ollama reasoning-model heuristic regex (`/r1/`) that misidentified unrelated models as thinking models
  110. The strictness ("assume everything is broken until proven otherwise") is what makes it work.
  111. ### `debugger` saves you from face-plants
  112. Twice during one bug-hunting session, the author was about to submit PRs based on seemingly clear reproductions. Both times `debugger` traced the behavior on HEAD and found the bugs had **already been silently fixed** in recent commits — the original reporters were on outdated versions. Submitting would have been embarrassing.
  113. - **Svelte #18083** — infinite-loop reconcile bug. Turned out to be a regression introduced in 5.43.8 that was fixed in 5.44.0+ by #17191 / #17240 / #17550. `debugger` ran the repro on HEAD and the test passed.
  114. - **Mermaid #6953** — sequence diagram alias+type combo. Already shipped in 11.14.0 via PR #7136; the issue just hadn't been closed.
  115. The slow methodology ("reproduce, then hypothesize, then verify") is the whole point.
  116. ### `planner` replaces the clarification loop
  117. On tasks touching 3+ files, dispatching to `planner` first turns a 30-message back-and-forth into one structured Task Prompt. The **six-element contract** (goal / scope / input / output / acceptance / boundaries) forces you to state the Definition of Done before anyone writes code.
  118. ### `vuln-verifier` is boring in the best way
  119. Most reported "vulnerabilities" are false positives or partially true. The **PoC-or-it-didn't-happen** protocol converts fuzzy "I think this could be exploited" reports into verdicts with actual program output. Every verdict comes with an attack input **and** a baseline control input — so you prove the vulnerable behavior is triggered by the attack and not by any input.
  120. ---
  121. ## Install (One Command)
  122. ```
  123. /plugin marketplace add NYCU-Chung/my-claude-devteam
  124. /plugin install devteam@my-claude-devteam
  125. ```
  126. Once installed, all 12 agents and 15 hooks register automatically. Restart Claude Code and your dev team is online.
  127. ### Optional: install the methodology document
  128. The plugin ships with the **P7/P9/P10 methodology + three red lines** baked into each agent, but for the strongest effect, also drop one of the `CLAUDE.md` files into `~/.claude/CLAUDE.md` so the whole session operates under the same discipline:
  129. ```bash
  130. # English
  131. curl -sL https://raw.githubusercontent.com/NYCU-Chung/my-claude-devteam/main/CLAUDE.en.md -o ~/.claude/CLAUDE.md
  132. # Traditional Chinese
  133. curl -sL https://raw.githubusercontent.com/NYCU-Chung/my-claude-devteam/main/CLAUDE.zh-TW.md -o ~/.claude/CLAUDE.md
  134. ```
  135. ### Manual install (without plugin)
  136. If you prefer not to use the plugin system:
  137. ```bash
  138. git clone https://github.com/NYCU-Chung/my-claude-devteam ~/my-claude-devteam
  139. mv ~/.claude/agents ~/.claude/agents.bak 2>/dev/null
  140. mv ~/.claude/hooks ~/.claude/hooks.bak 2>/dev/null
  141. cp -r ~/my-claude-devteam/agents ~/.claude/
  142. cp -r ~/my-claude-devteam/hooks ~/.claude/
  143. cp ~/my-claude-devteam/settings.example.json ~/.claude/settings.json
  144. # (optional) cp ~/my-claude-devteam/CLAUDE.en.md ~/.claude/CLAUDE.md
  145. ```
  146. **Verify the install:**
  147. ```
  148. You: "I need to add a POST endpoint for broadcast messages"
  149. Claude: [spawns fullstack-engineer with P7 methodology]
  150. [designs → implements → three-question self-review]
  151. [spawns critic for pre-deploy review]
  152. ```
  153. ---
  154. ## What's NOT Included
  155. This repo is **opinionated methodology + tools**, not a kitchen sink. You still need to bring:
  156. - **Your own subagents** for project-specific roles (VPS ops, deployment automation, custom integrations)
  157. - **Your own hook configuration** for paths and thresholds
  158. - **Your own CLAUDE.md project sections** — infrastructure, repo lists, deployment commands (keep these out of the public repo for security)
  159. - **Third-party skill packs** — this repo doesn't redistribute other people's work
  160. ---
  161. ## Credits
  162. - **P7/P9/P10 methodology and PUA mode** are adapted from [**tanweai/pua**](https://github.com/tanweai/pua) (MIT License) by 探微安全实验室 (Tanwei Security Lab). The original is a full Claude Code plugin with KPI reports, leaderboards, self-evolution tracking, and a Loop mode. If you want the full feature set, install it directly from [openpua.ai](https://openpua.ai).
  163. - **The 12-agent team structure and hooks** are the result of months of real-world iteration — shipping to production, getting burned, iterating again.
  164. - **Core philosophy** is inspired by Chinese big-tech engineering culture: P-level role ladders, closure-oriented task management, the "three red lines" discipline, and the corporate pressure culture that turns "good enough" into "exhaust every option".
  165. ---
  166. ## License
  167. MIT. Take it, fork it, ship it. Attribution appreciated but not required.
  168. ---
  169. > Built by [@NYCU-Chung](https://github.com/NYCU-Chung).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.