Borrowing it
Nothing to install: this file belongs to Stanshy/AgentHub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Stanshy/AgentHub/main/CLAUDE.mdgit clone --depth 1 https://github.com/Stanshy/AgentHubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/stanshy/agenthub/claude-md)<a href="https://agentmods.dev/instructions/stanshy/agenthub/claude-md"><img src="https://agentmods.dev/badge/instructions/stanshy/agenthub/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/stanshy/agenthub/claude-md"><img src="https://agentmods.dev/badge/instructions/stanshy/agenthub/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01049 | $0.01049 |
| Opus 5.5 | $0.00420 | $0.00420 |
| Sonnet 5.5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
AgentHub CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentHub — Agent 指南（索引）
本文件是地圖，不是百科全書。詳細規範見索引指向的 .knowledge/ 文件。 所有 Agent 執行任務前必須先閱讀本文件，再依索引查閱對應文件。
🚀 首次 clone 後請執行：
bash scripts/install-skills.sh（將公司級 Skills 安裝到全域~/.claude/commands/）
專案簡介
- 專案名稱: AgentHub (Maestro v2)
- 類型: Electron 桌面應用（AI Agent 團隊管理平台）
- 核心價值: 用 Harness（Skill + Hook + FileWatcher）驅動虛擬開發公司，GUI 只做監控和 3 個操作
- 目標用戶: 老闆（一人公司創辦人）
- 開發平台: Windows 11
最高原則（3 條致命規則）
-
文件就是法律 — 程式碼必須與規範文件一致，不一致以文件為準。 → 完整 8 條規則見
.knowledge/doc-governance.md -
IPC 四方同步 —
ipc.ts→preload.ts→useIpc.ts→env.d.ts缺一不可。 → 詳見.knowledge/architecture.md「IPC 三方一致規則」 -
不確定就去讀，不要猜 — 不得憑空想像任何資料結構或 API 格式。 → 真相來源表見
.knowledge/coding-standards.md「禁止憑空想像規則」
※ 危險指令已由 PreToolUse Hook 強制攔截（kill-port / --no-verify / force push main），見
.claude/settings.json
常用指令
npm run dev # 啟動開發模式
npm run test # 單元測試
npm run lint # ESLint 檢查
npm run typecheck # TypeScript 型別檢查
npm run build # 打包
專案文件索引
專案級規範（.knowledge/）
| 文件 | 用途 | 版本 |
|---|---|---|
.knowledge/project-overview.md |
專案概述、目標、技術棧、v1→v2 變更摘要 | v1.1 |
.knowledge/architecture.md |
系統架構、服務清單、IPC 架構、三方一致規則 | v1.1 |
.knowledge/directory-structure.md |
目錄結構詳細說明 | v1.0 |
.knowledge/coding-standards.md |
編碼規範、命名、Commit 紀律、依賴規則、禁止憑空想像 | v1.1 |
.knowledge/testing-standards.md |
測試策略與規範 | v1.0 |
.knowledge/quality-checklist.md |
G0-G6 品質檢查清單 | v1.0 |
.knowledge/postmortem-log.md |
踩坑快速參考 + 歷史紀錄 | v1.1 |
.knowledge/doc-governance.md |
文件治理 8 條完整規則 | v1.0 |
.knowledge/team-hierarchy.md |
團隊架構、指揮鏈、Sprint 概覽 | v1.0 |
公司規範（.knowledge/company/）
| 文件 | 用途 |
|---|---|
.knowledge/company/sop/sprint-planning.md |
Sprint 規劃 SOP v4.1 |
.knowledge/company/sop/code-review.md |
程式碼審查 SOP |
.knowledge/company/standards/coding-standards.md |
公司編碼標準 |
.knowledge/company/standards/api-standards.md |
公司 API 標準 |
.knowledge/company/standards/quality-checklist.md |
公司品質檢查清單 |
.knowledge/company/standards/project-rules.md |
子專案共用開發規則 |
.knowledge/company/standards/team-workflow.md |
子專案共用團隊流程 |
.knowledge/company/templates/sprint-proposal.md.template |
Sprint 提案書範本 |
.knowledge/company/templates/dev-plan.md.template |
開發計畫書範本 |
.knowledge/company/templates/internal-review.md.template |
內部審查報告範本 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 78 lines · 1,049 tokens per session scan A 155895bdb8b7
AgentHub CLAUDE.md is an instructions file published in the GitHub repository Stanshy/AgentHub (204 stars, last pushed 6mo ago), licensed MIT. It adds 1,049 tokens to every session, about $0.0042 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).