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/ihabkhaled/clawai/claude-mdgit clone --depth 1 https://github.com/ihabkhaled/ClawAIWrote 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/ihabkhaled/clawai/claude-md)<a href="https://agentmods.dev/instructions/ihabkhaled/clawai/claude-md"><img src="https://agentmods.dev/badge/instructions/ihabkhaled/clawai/claude-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 | $0.04872 | $0.04872 |
| Opus 5 | $0.02436 | $0.02436 |
| Sonnet 5 | $0.00974 | $0.00974 |
| Haiku 4.5 | $0.00487 | $0.00487 |
Grade A, and why
ClawAI CLAUDE.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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawAI — root policy
Canonical entry point for every agent. This file is an index, not a mirror: it
carries only what you need before you know what you are doing, plus links to the
canonical body for everything else. Rule bodies live in rules/, runbooks in
skills/, structural maps in context/, narrative in docs/.
It was 2,595 lines and 167 kB, which spent a large slice of every agent's context
window on every task and drifted out of step with the rules/ files it duplicated.
Nothing was deleted — each section below links to the canonical home its content
moved to.
Identity
Local-first AI orchestration platform. 18 NestJS services + Next.js 16 frontend +
6 shared packages (npm workspaces). 14 PostgreSQL (pgvector) + MongoDB + Redis +
RabbitMQ (claw.events, topic exchange) + Ollama. Nginx terminates TLS on 443 and
proxies /api/v1/* to services on 4001–4018.
Details: context/architecture-map.md ·
context/service-catalog.md ·
context/workspace-map.md ·
context/port-and-service-map.md
Authority hierarchy (higher wins on conflict)
- This file
rules/00-non-negotiable-rules.md— the blockerscontext/architecture-map.md+context/stack-and-toolchain.md- Numbered
rules/*→skills/*→context/*+memory/* - Generated
.ai/manifests/* - Compact per-tool routers (
CODEX.md,cursor.md,GEMINI.md,KIMI.md,GLM.md,QWEN.md,DEEPSEEK.md,MISTRAL.md,AGENTS.md,.cursorrules)
First command, always
npm run knowledge:context -- --task="<what you are doing>"
Then read .ai/local/current-context.md. It resolves the affected workspaces,
governing rules, matching skills, reviewers, related events/permissions/env vars,
and known pitfalls for your specific task. Compact bootstrap: .ai/BOOTSTRAP.md.
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 Changed · +2 lines · +156 tokens per session 385410530909
- 5d ago First seen · 244 lines · 4,716 tokens per session scan A f4aa02bba596
ClawAI CLAUDE.md is an instructions file published in the GitHub repository ihabkhaled/ClawAI (22 stars, last pushed today), licensed Apache-2.0. It adds 4,872 tokens to every session, about $0.0244 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
Khala-Agentic-AI-Teams CLAUDE.md
Claude Code instructions for brandonkindred/Khala-Agentic-AI-Teams, covering claude.md, project overview, repository structure, architecture and build & run.
ai-agents voice.instructions.md
Instructions for rjmurillo/ai-agents, covering voice, definitions, tier and tension, lead with the point and be concrete.
ai-agents code-quality.instructions.md
Baseline code quality rules merging Clean Code and Code Complete fundamentals. Apply on every code edit.
ai-agents push-lock.instructions.md
Instructions for rjmurillo/ai-agents, covering one push lock path, must, must not, historical measurements and commit guard.
ai-agents plugin-version-bump.instructions.md
Instructions for rjmurillo/ai-agents, covering plugin manifests carry no version, why, what a pr does now, if instructions say to bump, they are stale and checking.
ai-agents unified-software-engineering.instructions.md
Unified software engineering rules synthesized from classic engineering literature. Apply when principles appear to conflict, when scoping work, or when judging whether a pattern in a diff should be allowed. Use as the default tiebreaker, not as an additional layer on top of every specialized rule.