Borrowing it
Nothing to install: this file belongs to tiangong-ai/skills. 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/tiangong-ai/skills/main/AGENTS.mdgit clone --depth 1 https://github.com/tiangong-ai/skillsWrote 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/tiangong-ai/skills/agents-md)<a href="https://agentmods.dev/instructions/tiangong-ai/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/tiangong-ai/skills/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 5.1 | $0.01238 | $0.01238 |
| Opus 5 | $0.00619 | $0.00619 |
| Sonnet 5 | $0.00248 | $0.00248 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
skills 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tiangong AI Skills Agent Contract
本仓库负责可复用 agent skills。workspace 根仓负责子模块集成与交付治理； skill 内容、skill 规范、marketplace 元数据和本仓文档治理属于本仓库。
Required Load Order
- 阅读本文件。
- 阅读
.docpact/config.yaml。 - 对计划修改的路径，在本仓根目录运行
docpact route --root . --paths <target-paths> --format json。 - 阅读
_docs/contracts/**、_docs/architecture/**、_docs/runbooks/**中与 route 结果相关的文档。 - 如果任务涉及新建或修改 skill，继续按下方现有
skill-creator强制规则执行。
Source Of Truth
.docpact/config.yaml：机器可读治理规则、route alias、coverage、 doc inventory 与 freshness 策略。README.md/README.zh-CN.md：安装、更新、环境变量和使用说明。_docs/contracts/repo-contract.md：本仓边界、skill 规范与完成条件。_docs/architecture/repo-architecture.md：skill 仓库结构和分发拓扑。_docs/runbooks/development.md：创建、校验、生成 agent 配置和交付流程。_docs/architecture/atomic-data-capabilities.md：原子数据 Skill 与 CLI/Research 的目标边界。_docs/runbooks/atomic-data-skill-migration.md：数据 Skill 分类、批次、PR 依赖和 迁移验收流程。
Hard Boundaries
- 不要把 workspace 子模块策略、分支策略或集成完成规则复制进本仓。
- 不要绕过
skill-creator规范手写不合规 skill。 - 不要提交真实 API key、账号密码或用户私有数据到 skill 资源中。
- 修改 skill 触发条件、脚本、引用资料、agent 配置或 marketplace 元数据时， 同步检查本仓 docs 和 docpact route 结果。
- 原子数据机器契约、connector、Schema、凭证和运行回执属于 Tiangong CLI； 数据 Skill 只保留语义入口和可检验的 capability/operation contract-major requirement。 实际 CLI package 由调用方或 workspace runtime lock 负责，不下沉到每个 Skill。
Completion Criteria
- 修改前已查看相关
docpact route输出。 - route 命中的文档已 reviewed 或 updated。
- 治理变更后
docpact validate-config --root . --strict通过。 - skill 变更按
skill-creator流程运行对应校验。 - 数据 Skill 迁移还必须验证稳定 requirement，并用仓库级 migration provenance 对 exact CLI capability/operation/Schema 做一次发布资格审计；只有对应 CLI 正式版本 可安装后才能移除旧执行脚本。普通兼容 CLI 发布不要求重写全部 Skill requirement。
tsinghua-graduate-thesis的 PDF renderer 或视觉 QA 变更必须用仓库内隐私安全的真实二进制 PDF fixture，在其 targeted clean-container 中先观察 RED、再在新容器中转 GREEN；PR 前还要运行全仓 cold gate。- Auto Research 及其直接 evidence wrapper 的变更必须先在
scripts/test-clean-container.sh创建的独立、无宿主 HOME/全局 Skill/CLI/runtime cache 的容器中观察回归测试失败，再在另一个新容器中转绿； 构建可复用输入未变化的 Docker layer，宿主测试不能替代。 - 该容器必须运行
academic-paper-download/scripts/tests的完整 unittest discovery；测试镜像只安装requirements.lock中哈希锁定的核心依赖，绝不安装 可选 CloakBrowser 运行时或浏览器二进制。 - 修改
.dockerignore、Dockerfile.clean-test、依赖输入，或准备 PR/发布时， 必须额外运行scripts/test-clean-container.sh --cold-build验证冷构建路径。
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 · -2 tokens per session 0dc256ada57d
- yesterday Changed · +3 tokens per session 5bba00dd31b2
- 4d ago Changed · -1 tokens per session b8b6f1ad5088
- 4d ago Changed · -3 tokens per session f81b8d1bdd0f
- 5d ago Changed · +16 lines · +247 tokens per session 43b7af3cd495
- 8d ago First seen · 78 lines · 994 tokens per session scan A 24de1fc1a946
skills AGENTS.md is an instructions file published in the GitHub repository tiangong-ai/skills (9 stars, last pushed yesterday), licensed MIT. It adds 1,238 tokens to every session, about $0.0062 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.