agentmods.dev

OpenClawn: Instructions file for Claude Code

CLAUDE.md

OpenClawn CLAUDE.md is an instructions file for Claude Code from MuhammadHasbiAshshiddieqy/OpenClawn. It costs 6,049 tokens per session, scanned A, original, MIT.

A project guide for coding agents working on OpenCLAWN, an AI-agent framework built with Python, FastAPI, HTMX, and SQLite.

In plain words
What is it for?
Building and maintaining OpenCLAWN while following its architecture, multi-tenant setup, user roles, login system, policy engine, and event-driven runtime.
Why use it?
It gives agents the project’s required rules, design specification, coding conventions, and implementation order before they change code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is MuhammadHasbiAshshiddieqy/OpenClawn's own configuration. It tells Claude Code how to work on OpenClawn itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OpenClawn configures →

not rated 16repo 2d ago A scan 6,049 tokens original MIT
View source ↗ MuhammadHasbiAshshiddieqy/OpenClawn
Reuse

Borrowing it

Nothing to install: this file belongs to MuhammadHasbiAshshiddieqy/OpenClawn. 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/MuhammadHasbiAshshiddieqy/OpenClawn/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MuhammadHasbiAshshiddieqy/OpenClawn

Made for: Claude Code.

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.

agentmods badge for OpenClawn CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/muhammadhasbiashshiddieqy/openclawn/claude-md/github.svg)](https://agentmods.dev/instructions/muhammadhasbiashshiddieqy/openclawn/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/muhammadhasbiashshiddieqy/openclawn/claude-md"><img src="https://agentmods.dev/badge/instructions/muhammadhasbiashshiddieqy/openclawn/claude-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.

agentmods 80×15 button for OpenClawn CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/muhammadhasbiashshiddieqy/openclawn/claude-md"><img src="https://agentmods.dev/badge/instructions/muhammadhasbiashshiddieqy/openclawn/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,049 This file is loaded in full into every session.
When invoked 6,049 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06049 $0.06049
Opus 5 $0.03024 $0.03024
Sonnet 5 $0.01210 $0.01210
Haiku 4.5 $0.00605 $0.00605

Measured 12d ago against content hash a226d64ecb50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

OpenClawn 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 12d 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.

CLAUDE.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Panduan Implementasi OpenCLAWN

File ini adalah panduan operasional untuk agent coding (Claude Code / Sonnet / model lain) yang mengimplementasikan OpenCLAWN.

Cara pakai: Bawa file ini + openclawn-core-spec-v0.4.md ke repository baru. Dua file ini cukup untuk memberi konteks penuh tanpa membawa riwayat percakapan. Baca kedua file sebelum menulis kode apa pun.

Aturan emas: Spec (openclawn-core-spec-v0.4.md) adalah sumber kebenaran untuk APA yang dibangun. File ini (CLAUDE.md) adalah sumber kebenaran untuk BAGAIMANA membangunnya — konvensi, urutan kerja, dan hal yang tidak boleh dilanggar.

Catatan versi: openclawn-core-spec-v0.3.md adalah blueprint greenfield asli (Sprint 0–4) — dipertahankan sebagai catatan sejarah, TIDAK lagi mencerminkan kode saat ini. v0.4 adalah spec yang mengikat kondisi kode sekarang (v0.12.0): multi-tenant, RBAC, OIDC, Policy Engine, Event-Driven Runtime, 5 role, dll.

0. TL;DR untuk agent yang baru masuk

Kamu sedang membangun OpenCLAWN: framework agent AI yang ringan, aman, self-improving, dan multi-role. Python 3.12, FastAPI + HTMX, SQLite, hybrid LLM (Ollama lokal + Claude API).

Yang membuat proyek ini berbeda adalah 4 inovasi inti:

  1. Routing audit + self-calibration — catat setiap keputusan routing + apakah terbukti tepat
  2. Skill decay — skill yang jarang dipakai memudar dan ter-arsip
  3. Confidence-gated crystallization — agent menilai kualitas solusinya sebelum menyimpannya sebagai skill
  4. Role output contracts — handoff antar role tervalidasi dengan Pydantic

Empat inovasi ini bukan fitur tambahan — mereka adalah inti dari nilai proyek. Jangan pernah memangkasnya demi "menyederhanakan".

Mulai dari Sprint 0 di §21 spec. Jangan loncat. Bangun fondasi (infra/) dulu, baru yang lain.

1. Prinsip yang tidak boleh dilanggar

Urut berdasarkan prioritas. Jika dua prinsip bertabrakan, yang lebih atas menang.

  1. Keamanan dulu. code_run HARUS berjalan di dalam Docker sandbox (--network none, --read-only, non-root, timeout). Tidak ada eksekusi kode di host. Tidak pernah. Lihat spec §12.
  2. Credential tidak pernah masuk context/prompt. Hanya diinjeksi saat outbound request via Vault. Jangan pernah log API key. Jangan pernah taruh di tabel DB.
  3. Setiap dependency eksternal punya kegagalan yang anggun. LLM call → retry + fallback chain. Ollama offline ≠ agent mati. Lihat spec §9.
  4. Token-first. Sebelum menambah apa pun ke context window, tanya: apakah ini perlu? Target < 28K token. Aktifkan prompt caching untuk bagian stabil.
  5. Tidak ada hardcoded domain/locale. OpenCLAWN harus netral. Tidak ada "ServisIn", tidak ada "Depok", tidak ada Bahasa Indonesia yang dipaksakan di core. Locale via field locale, bukan di kode.
  6. Setiap inovasi = modul yang bisa diekstrak. Tulis skill_decay.py, audit.py, crystallizer.py, contracts.py sedemikian rupa sehingga suatu hari bisa dijadikan paket terpisah. Jangan bocorkan ketergantungan spesifik OpenCLAWN ke dalamnya selain lewat interface yang jelas (DatabaseManager).

Read the full file on GitHub · 347 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.

  1. 12d ago First seen · 347 lines · 6,049 tokens per session scan A a226d64ecb50

Subscribe to this mod's changes

OpenClawn CLAUDE.md is an instructions file published in the GitHub repository MuhammadHasbiAshshiddieqy/OpenClawn (16 stars, last pushed 2d ago), licensed MIT. It adds 6,049 tokens to every session, about $0.0302 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.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens