Borrowing it
Nothing to install: this file belongs to TokenDanceLab/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/TokenDanceLab/AgentHub/master/AGENTS.mdgit clone --depth 1 https://github.com/TokenDanceLab/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/tokendancelab/agenthub/agents-md)<a href="https://agentmods.dev/instructions/tokendancelab/agenthub/agents-md"><img src="https://agentmods.dev/badge/instructions/tokendancelab/agenthub/agents-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/tokendancelab/agenthub/agents-md"><img src="https://agentmods.dev/badge/instructions/tokendancelab/agenthub/agents-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 | $0.02456 | $0.02456 |
| Opus 5.5 | $0.00982 | $0.00982 |
| Sonnet 5.5 | $0.00491 | $0.00491 |
| Haiku 4.5 | $0.00246 | $0.00246 |
Grade A, and why
AgentHub AGENTS.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 9d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AgentHub 项目总规则唯一入口
最后更新：2026-10-18
根级 Agent 规则只写硬边界、工作流和 owner 指针；实现细节、CI 长表和发布步骤在各自 owner 文档。
0. 事实源与加载顺序
- 维护者即时指令。
AGENTS.md：项目硬边界、工作流、验证纪律和索引。- GitHub issue/PR：当前任务、进度、阻塞和验收证据。
api/、docs/architecture.md、docs/architecture/：契约与架构事实。- 其他 owner 文档。
动态状态必须现场重读，禁止依据历史记录、提交信息或本地缓存推断。
1. 新 Agent 90 秒入口
- 先跑
git status --short --branch、git log -5 --oneline、git worktree list，确认真实分支、脏文件和并行 worktree。 - 读本文件，再读 GitHub 当前 issue/PR；复杂任务先确认目标、允许修改路径、禁改路径和验收命令。
- 只加载与任务直接相关的一个 owner 文档；已经能回答“目标 / owner / 写集 / 验收”就停止扩展上下文。
- 最窄验证先行；宣称 merge-ready、真实 E2E、发布或生产就绪前，再跑对应完整 gate。
- 进度以 GitHub issue/PR 为准。
任务路由：接口改动读 api/openapi.yaml、api/events.md、api/conventions.md；前端数据流读 docs/architecture/04-frontend-data-flow.md；身份授权读 docs/architecture/06-auth-identity.md；宏观协议/一致性/代理权读 docs/architecture/10-macro-engineering-design.md。人类开发者入口是 README.md → docs/architecture.md → docs/developer-quickstart.md。
2. 架构与产品边界
- Hub Server / Edge Server 使用 Go；UI 使用 React + TypeScript；Desktop 使用 Tauri；主协议是 REST JSON + typed WebSocket。
- API 契约 SSOT 在
api/；Hub REST/WS 前端实现 SSOT 在app/shared/src/hub/hubClient.ts，各平台hubClient.ts只能保留平台胶水。 - 通用 UI、transcript、composer、inspector、platform contract 放
app/shared/；端级 shell 放app/workbench/，依赖方向只能 workbench → shared。 - Desktop native 能力只在
app/desktop/src-tauri/；renderer 不获得 raw process 权限。本地执行由 Local Edge / typed Tauri host API 承担。 - Web 与 Mobile 都是 Hub-only，不直连 Local Edge、raw runtime 或 Desktop host；Mobile 当前是 fixture/边界验证 lane，不是 release candidate。
- 本地执行不依赖 Hub；Hub 负责账号、IM、多端同步、远程查看/审批、设备路由、中继和审计。
宏观设计以 docs/architecture/10-macro-engineering-design.md 为 SSOT，硬边界只有这些：Hub 是控制面而非模型 Turn 执行器；调度/审批由确定性状态机决定；Hub→Edge 交付要可重试、幂等、可审计；授权采用 task-scoped / per-action 最小代理权；run/tool/model/token/cost 观测遵循既定 OTel GenAI 口径。产品模型与术语见 docs/architecture.md。
3. 生态与真实性边界
- 登录只接 TokenDance ID；TokenDance ID 证明身份，Hub 用本地 membership/resource/action 做授权。第三方绑定归身份系统，不在 AgentHub 复制第二套登录。
- TokenDance API/Gateway key 不是 ID token，不得暴露给浏览器、Agent context、sandbox 或公开日志。
- Feishu/Lark 是协作入口，不是第二身份系统；身份绑定归 TokenDance ID。
- stub/demo/fixture/readiness-only 不得冒充真实登录、真实模型/API、packaged Desktop 或生产发布。
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.
- 9d ago Changed · -3 lines · -146 tokens per session 07bd0237a531
- 1mo ago Changed · -170 lines · -4,417 tokens per session a0959c44b995
- 1mo ago Changed · +1 lines · +296 tokens per session 0bf0f41e183b
- 1mo ago First seen · 285 lines · 6,723 tokens per session scan A 97d3c522ad16
AgentHub AGENTS.md is an instructions file published in the GitHub repository TokenDanceLab/AgentHub (10 stars, last pushed today), licensed Apache-2.0. It adds 2,456 tokens to every session, about $0.0098 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 2026-08-31.
Other instructions, from other repositories
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.