ClawDev AGENTS.md

Project instructions for ClawDev, a Python framework that connects OpenClaw agents with several collaborating agents and staged work such as analysis, coding, review, and testing. They also describe running the project tools inside Docker containers.

In plain words
What is it for?
Use them when changing ClawDev, communicating with OpenClaw agents, working on its collaboration flow, or running Python tests and lint checks in Docker.
Why use it?
They provide the project's architecture and exact container-based checks, reducing the risk of using the wrong environment or missing required tests and linting.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/hdanzz/clawdev/agents-md
Clone the repo
git clone --depth 1 https://github.com/HDAnzz/ClawDev

Made for: Codex, OpenCode.

Per session 3,440 This file is loaded in full into every session.
When invoked 3,440 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03440 $0.03440
Opus 5 $0.01720 $0.01720
Sonnet 5 $0.00688 $0.00688
Haiku 4.5 $0.00344 $0.00344

Measured yesterday against content hash 69f31e179fb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ClawDev 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.

AGENTS.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - ClawDev Project Guidelines

Project Overview

This project (clawdev) is a Python framework that combines OpenClaw ACP (Agent Client Protocol) with a multi-agent collaboration system for automated code generation. It provides:

  • ACP client for communicating with OpenClaw agents
  • ChatChain orchestration for managing multi-agent dialog workflows
  • Phase-based development process (demand analysis, coding, review, testing, etc.)

The main entry point is src/main.py and the core packages are src/openclaw_acp/ and src/clawdev/.

Build, Lint, and Test Commands

Running Tests and Linting in Docker Container

The project runs in Docker. Code directory is mounted at /app/ClawDev in the container. Always use docker exec to run tools from the project's virtual environment to avoid corrupting the local venv.

# Run all tests in docker container
docker exec -w /app/ClawDev clawdev-openclaw-gateway-1 /app/ClawDev/.venv/bin/pytest tests/ -v

# Run a single test file
docker exec -w /app/ClawDev clawdev-openclaw-gateway-1 /app/ClawDev/.venv/bin/pytest tests/test_agent.py -v

# Run linting in docker container
docker exec -w /app/ClawDev clawdev-openclaw-gateway-1 /app/ClawDev/.venv/bin/ruff check src/ tests/

Code Style Guidelines

General Principles

  • Follow Python's PEP 8 style guide
  • Use type hints for all function parameters and return values
  • Write concise, readable code
  • Keep functions focused and single-purpose

Naming Conventions

  • Classes: PascalCase (e.g., OpenClawAgent)
  • Functions/variables: snake_case (e.g., gateway_url, async_step)
  • Constants: UPPER_SNAKE_CASE (e.g., MAX_RETRIES)
  • Private methods: prefix with underscore (e.g., _initialize)

Import Organization

Order imports in the following groups (separate each group with a blank line):

  1. Standard library imports
  2. Third-party imports
  3. Local application imports (relative imports)
import asyncio
import json
import os
from queue import Queue, Empty
from typing import AsyncGenerator, Callable, Optional

from .utils import require_api_key

Read the full file on GitHub · 391 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. yesterday First seen · 391 lines · 3,440 tokens per session scan A 69f31e179fb6

Subscribe to this mod's changes

ClawDev AGENTS.md is an instructions file published in the GitHub repository HDAnzz/ClawDev (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 3,440 tokens to every session, about $0.0172 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 2026-08-31.

Related

Other instructions, from other repositories

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 · 5,182 tokens

buildNext

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

next.js 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

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

spec-kit 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 · 7,040 tokens

langchain 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 · 4,345 tokens