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/openclaw/clawpatch/agents-mdgit clone --depth 1 https://github.com/openclaw/clawpatchWhat 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 | $0.00578 | $0.00578 |
| Opus 5 | $0.00289 | $0.00289 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
clawpatch 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 yesterday.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
clawpatch is a TypeScript CLI. Source lives in src/, with the CLI entry in
src/cli.ts, workflow orchestration in src/app.ts and src/workflow.test.ts,
and feature mappers under src/mappers/. Tests sit beside implementation files
as *.test.ts. Build output is generated into dist/ and should not be edited.
User documentation is in docs/; the static website assets are in website/.
Build, Test, and Development Commands
Use pnpm with Node 22 or newer.
pnpm build: clean and compile the package withtsconfig.build.json.pnpm typecheck: run TypeScript checks without emitting files.pnpm lint: run Oxlint usingoxlint.json.pnpm format: rewrite files with Oxfmt.pnpm format:check: verify formatting without writing changes.pnpm test: run the Vitest suite.pnpm test src/mapper.test.ts: run one focused test file.
For local CLI checks, build first, then run node dist/cli.js <command>.
Coding Style & Naming Conventions
Write ESM TypeScript. Prefer small pure helpers, explicit return values for
shared functions, and existing mapper patterns before adding new abstractions.
Use two-space indentation as enforced by Oxfmt. Name files by domain
(provider.ts, detect.ts, mappers/python.ts) and keep tests named
<module>.test.ts. Keep generated output, local state, and fixture churn out of
commits unless the change explicitly requires it.
Testing Guidelines
Vitest is the test framework. Add or update focused tests for any behavior
change, especially mapper coverage, workflow state transitions, provider command
construction, and validation behavior. Prefer targeted test runs while
developing, then run pnpm typecheck && pnpm lint && pnpm test && pnpm build
before handing off.
Commit & Pull Request Guidelines
History uses short semantic subjects such as fix(provider): quote codex exec args correctly on Windows and feat(mapper): support monorepo Next project mapping. Keep commits scoped and descriptive. PRs should explain the behavior
change, link related issues, mention user-facing docs or changelog updates when
needed, and include the exact checks run. Add screenshots only for website or
rendered-doc changes.
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.
- yesterday First seen · 56 lines · 578 tokens per session scan A 1cf859646842
clawpatch AGENTS.md is an instructions file published in the GitHub repository openclaw/clawpatch (810 stars, last pushed 4d ago), licensed MIT. It adds 578 tokens to every session, about $0.0029 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 2026-08-30.
Other instructions, from other repositories
clawsweeper AGENTS.md
Instructions for openclaw/clawsweeper, covering agents.md, structure, operating model, safety rules and pr validation and landing.
ccxt CLAUDE.md
Instructions for ccxt/ccxt, covering ccxt — repository guide for contributors and ai agents, 1. architecture, rest vs pro (websocket), per-language model and two transpilers.
Undefined CLAUDE.md
Instructions for 69gg/Undefined, covering claude.md, 项目概述, 开发命令, 依赖安装 / 初始化 and 启动.
yutu AGENTS.md
Instructions for eat-pray-ai/yutu, covering yutu, quick reference, directory index, documentation and conventions.
Undefined AGENTS.md
Instructions for 69gg/Undefined, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and tools & features.
telegram-bot AGENTS.md
Instructions for vendelieu/telegram-bot, covering agents.md, dev environment, testing, project structure and key conventions.