What is ClawAI AGENTS.md?

Repository instructions for ClawAI, a local-first platform that coordinates many services and a web interface through message-based communication.

Use them to find the affected workspaces, understand the service architecture, and follow the project's required context and engineering rules.

They identify the authoritative project documents and the required first steps before changing code in its monorepo, a repository containing multiple related projects.

How ihabkhaled/ClawAI configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ihabkhaled/ClawAI. 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/ihabkhaled/ClawAI/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ihabkhaled/ClawAI

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/ihabkhaled/clawai/agents-md/github.svg)](https://agentmods.dev/instructions/ihabkhaled/clawai/agents-md)

Your own site

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

Per session 1,611 This file is loaded in full into every session.

When invoked 1,611 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	$0.01611	$0.01611
Opus 5.5	$0.00644	$0.00644
Sonnet 5.5	$0.00322	$0.00322
Haiku 4.5	$0.00161	$0.00161

Measured 5d ago against content hash 156defe7a18c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ClawAI 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 5d 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 · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClawAI — agent router (canonical)

Every AI coding agent and every person starts here. This file routes; it does not restate policy. CODEX.md, GEMINI.md, DEEPSEEK.md, GLM.md, KIMI.md, MISTRAL.md and QWEN.md are generated from it; CLAUDE.md, cursor.md and .cursorrules add tool-specific notes and point back here (ADR-170).

Before you finish any change, update every doc it makes stale (rule 63). The hooks will reject it otherwise.

Testing is not optional. Unit tests are one of 15 QA lanes. Walk them all and record docs/qa-evidence/<date>-<slug>.md before calling anything done — start at QA-WORKFLOW.md (rules/60).

Identity

"Every AI, one workspace." Positioning: docs/01-executive-context/product-vision.md · flagships: docs/02-business-product/flagship-features.md. A local-first AI orchestration platform: NestJS services, a Next.js frontend and shared packages in one npm-workspace monorepo (live counts: .ai/manifests/repository.json). Events flow over RabbitMQ (claw.events); nginx proxies /api/v1/*. Map: context/architecture-map.md.

Authority (higher wins on conflict)

This router and rules/00-non-negotiable-rules.md
context/architecture-map.md and context/stack-and-toolchain.md
Numbered rules/ → skills/ → context/ + memory/
Generated .ai/manifests/*
Tool notes: CLAUDE.md, the generated per-model files, cursor.md, .cursorrules

First command, always

npm run knowledge:context -- --task="<what you are doing>"

Then read .ai/local/current-context.md: affected workspaces, governing rules, skills, reviewers, events, permissions, env vars and known pitfalls for the task. Compact bootstrap: .ai/BOOTSTRAP.md.

Read the full file on GitHub · 95 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.

5d ago Changed · +5 lines · +145 tokens per session 156defe7a18c
22d ago Changed · +20 tokens per session b4f77c6b6cf3
23d ago Changed · -114 lines · -1,236 tokens per session ec1c357ffd4b
1mo ago Changed 3e369368d331
1mo ago Changed 2546d9f09844
1mo ago Changed · +2 lines · +130 tokens per session 6126e34cafe4
1mo ago Changed · +4 lines · +63 tokens per session 72af9757e64c
1mo ago Changed · +7 lines · +136 tokens per session bf7e1ceb9921
2mo ago First seen · 191 lines · 2,353 tokens per session scan A 1dda71b3de77

Subscribe to this mod's changes

ClawAI AGENTS.md is an instructions file published in the GitHub repository ihabkhaled/ClawAI (24 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,611 tokens to every session, about $0.0064 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.

agentic-ai ai ai-agents ai-orchestration anthropic anthropic-claude

ClawAI AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ClawAI AGENTS.mdihabkhaled/ClawAI	Instructions file	24	3d ago	Apache-2.0	A	1,611	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	today	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

ClawAI: Instructions file for Codex