Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/tokendancelab/agenthub/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.svg" alt="Measured on agentmods" 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 | $0.07019 | $0.07019 |
| Opus 5 | $0.03510 | $0.03510 |
| Sonnet 5 | $0.01404 | $0.01404 |
| Haiku 4.5 | $0.00702 | $0.00702 |
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 today.
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 — 286 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
最后更新：2026-08-29
本文件是 AgentHub 的项目总规则唯一入口。Claude Code、Codex 和其他 Agent 都读本文件；本仓库不再维护 CLAUDE.md 或第二套根级规则。
0. 事实源优先级
- 管理员的直接指令
AGENTS.md- 项目规则、红线、工作流、skill 白名单、验证纪律- GitHub issues/PR - 当前专项进度、Issue/PR、阻塞、验收证据
docs/architecture.md+docs/architecture/- 架构、数据流、协议边界- 其他专题文档、
docs/decisions.md、reference、history
不要在治理报告或其他文档里复制本文件的规则。规则变更改这里；其他文档只链接或保留一句摘要。
0.5 根级目录地图
【活】= 维护中的源码/文档；【产物】= 构建/临时产物（gitignored，勿提交）。
| 目录 | 分类 | 职责 |
|---|---|---|
api/ |
活 | API 契约 SSOT（openapi.yaml/events.md/conventions.md） |
app/ |
活 | 前端 monorepo（web/desktop/mobile-rn/shared/workbench） |
| artifacts/ dist/ tmp/ | 产物 | 本地构建/临时输出（gitignored） |
docs/ |
活 | 知识库（architecture/governance/reference/archives） |
edge-server/ |
活 | Go Edge 服务（local runtime、adapters、lifecycle） |
hub-server/ |
活 | Go Hub 服务（REST/WS/OIDC/dispatch/agentteam） |
| node_modules/ | 产物 | 依赖（gitignored） |
pkg/ |
活 | Go 共享包（errcode 等） |
scripts/ |
活 | 验证/开发/发布脚本（verify/dev/e2e/git-hooks/lib/release/smoke/） |
tests/ |
活 | 跨服务测试 |
1. 首次入仓与渐进式加载
新 Agent 90 秒入口
- 先运行
git status --short --branch、git log -5 --oneline、git worktree list，确认真实分支、脏文件和并行 worktree；不要从旧 handoff 推断现场。 - 完整读本文件，再读 GitHub issues/PR 的当前目标与 active track。仓库根目录不维护第二份进度文件。
- 只在任务需要时读
docs/architecture.md和一个 owner 文档；不要先遍历整个docs/。 - 查明对应 Issue/PR、允许修改路径、禁改路径和验收命令后再动代码。没有活跃任务且范围复杂时，先建立短 spec 再动手。
- 每完成一个切片立即运行最窄验证；宣称 merge-ready、真实 E2E、发布或生产就绪前，再运行对应完整 gate。
停止加载规则：已经能回答“当前目标、事实 owner、允许改哪里、用什么验证”时就停止读文档；论证材料最多追加 1-3 篇精确 docs/reference/**，历史只通过 docs/history.md 定位。
人类同学的最短入口是 README.md → docs/architecture.md → docs/developer-quickstart.md。
任务路由：接口改动读 api/openapi.yaml、api/events.md、api/conventions.md；UI/数据流读 docs/architecture/04-frontend-data-flow.md；身份、授权、飞书、Gateway、安全、公开包装、i18n、设计 token 的跨产品边界读下方 §4 生态边界（TokenDance 系统级 docs 在私有 workspace，公开仓不复制其内容）。
2. 项目分工和边界
| 方向 | 负责范围 | 主要目录 |
|---|---|---|
| 前端 | Web 工作台、IM 交互、Diff/Preview/Approval、前端状态 | app/web/, app/shared/ |
| 后端 | Hub Server、TokenDance ID 接入、Edge-Hub 通信、同步、中继、审计 | hub-server/, edge-server/, api/ |
| Desktop | Tauri、Local Edge、本地 runtime、workspace、tray | app/desktop/, edge-server/ |
| Mobile | Expo/RN、OIDC deep-link、SecureStore、Notifications | app/mobile-rn/ |
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.
- today Changed · +1 lines · +296 tokens per session 0bf0f41e183b
- 4d 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 7,019 tokens to every session, about $0.0351 per session on Opus 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
wanwu-workflow CLAUDE.md
Instructions for UnicomAI/wanwu-workflow, covering claude.md, project overview, development commands, environment setup and clone and setup.
lightcode copilot-instructions.md
Instructions for Kartik-2239/lightcode, covering copilot instructions, build and test commands, high-level architecture and key conventions.
codexcw AGENTS.md
AGENTS.md instructions for c3-oss/codexcw, covering agents, project shape, build, test, develop, coding style and commits and prs.
codexcw CLAUDE.md
Claude Code instructions for c3-oss/codexcw: See AGENTS.md for the canonical guidance. Conventions, layout, commands, hooks, and release trains all live there.
agent-nexus AGENTS.md
Instructions for canoo/agent-nexus: This repository is managed by the NEXUS Framework (Network of EXperts, Unified in Strategy). For detailed operational instructions, agent personas, and workflow logic, please refer to the core definition file.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.