What is CrewClaw AGENTS.md?

Repository-specific instructions for CrewClaw, a platform for discovering, deploying, using, and evaluating AI employees. They describe the project's components, boundaries, commands, and employee-package rules.

Use them before changing CrewClaw to understand its employee specifications, registry, runtime, command-line workbench, evaluation system, and website rules.

They help coding agents preserve the project's division of responsibilities and follow its authoritative product requirements.

How staruhub/CrewClaw configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to staruhub/CrewClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/staruhub/CrewClaw/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/staruhub/CrewClaw

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/staruhub/crewclaw/agents-md/github.svg)](https://agentmods.dev/instructions/staruhub/crewclaw/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/staruhub/crewclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/staruhub/crewclaw/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/staruhub/crewclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/staruhub/crewclaw/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 762 This file is loaded in full into every session.

When invoked 762 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00762	$0.00762
Opus 5.5	$0.00305	$0.00305
Sonnet 5.5	$0.00152	$0.00152
Haiku 4.5	$0.00076	$0.00076

Measured 2mo ago against content hash e0254e7ad3a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

CrewClaw 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 2mo 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.

AGENTS.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project

This repo builds CrewClaw by ChaoGeek: an AI Employee Platform — discover, hire, deploy, use, and evaluate digital employees. One line: OpenCode makes AI able to work; OpenWork gives AI a computer; CrewClaw proves which AI employee deserves to be hired.

Components: the two-file employee standard (hire.yaml hiring contract + crewclaw.employee.yaml runtime spec, JSON Schemas in contracts/schema/), the employee registry + validator, the Node reference runtime (packages/runtime, TaskEvent JSONL), the Ratatui supervision workbench (crates/crewclaw-cli), the evaluation runner (real benchmark scores), and the local-first marketplace website (Vite + hono, real package downloads). Authoritative product doc: docs/prd_v0.20.md (versioned with the implementation; boundary charter included).

Boundaries (charter, 2026-07-10)

CrewClaw TUI = supervision cockpit (observe / control / accept). Built features stay; new features may only be simple preview/viewing. Editors, file managers, browsers, long-running execution belong to OpenWork — never rebuild them here.
Website = local-first storefront: a projection of the registry + real package downloads. Hosted marketplace (accounts/backend) is an explicit far-future milestone.
TaskEvent is additive-only: never change existing event semantics; add variants.
Honesty rules: use real data where it exists, label MOCK explicitly where it doesn't, never fabricate; a mock eval score never overwrites a real (mock:false) certification score.
Hermes Agent is the external runtime target. Do not fork or modify Hermes internals; do not write directly to ~/.hermes; use official hermes profile commands.
Do not commit .env, auth.json, memories, sessions, logs, state DBs, workspaces, or user data (single source: contracts/forbidden-paths.ts).

Commands

pnpm run check / pnpm run lint / pnpm test
pnpm run test:runtime / pnpm run test:conformance
cargo test --manifest-path crates/crewclaw-cli/Cargo.toml
pnpm run validate:all-experts
pnpm run schema:generate
pnpm eval:expert <slug> [--mock]
pnpm run test:e2e
pnpm run crewclaw list

Read the full file on GitHub · 57 lines

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.

2mo ago First seen · 57 lines · 762 tokens per session scan A e0254e7ad3a4

Subscribe to this mod's changes

CrewClaw AGENTS.md is an instructions file published in the GitHub repository staruhub/CrewClaw (24 stars, last pushed 12d ago), licensed Apache-2.0. It adds 762 tokens to every session, about $0.0030 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.

LLM agent-framework ai-agents ai-employee developer-tools local-first

CrewClaw AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
CrewClaw AGENTS.mdstaruhub/CrewClaw	Instructions file	24	12d ago	Apache-2.0	A	762	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

CrewClaw: Instructions file for Codex