ClawTeam-OpenClaw coordinates multiple command-line coding agents as a swarm that divides work, communicates, and combines results. Developers use it to orchestrate agents including OpenClaw, Claude Code, Codex, Hermes Agent, nanobot, and Cursor. The catalogue entries provide skills and instructions for working with this coordination system.
Borrowing it
Nothing to install: this file belongs to win4r/ClawTeam-OpenClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/win4r/ClawTeam-OpenClaw/main/CLAUDE.mdgit clone --depth 1 https://github.com/win4r/ClawTeam-OpenClawWrote 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/win4r/clawteam-openclaw/claude-md)<a href="https://agentmods.dev/instructions/win4r/clawteam-openclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/win4r/clawteam-openclaw/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 5.1 | $0.03463 | $0.03463 |
| Opus 5 | $0.01732 | $0.01732 |
| Sonnet 5 | $0.00693 | $0.00693 |
| Haiku 4.5 | $0.00346 | $0.00346 |
Grade A, and why
ClawTeam-OpenClaw 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this project is
clawteam is a Python CLI for orchestrating swarms of CLI coding agents (OpenClaw, Claude Code, Codex, Hermes, nanobot, Cursor, etc.). This repo is win4r/ClawTeam-OpenClaw — a fork of HKUDS/ClawTeam where the default agent is openclaw instead of claude. The +openclaw PEP 440 local identifier in the version (e.g. 0.3.0+openclaw1) must be preserved on bumps.
There is no server and no database. All state is JSON files under ~/.clawteam/ (overridable via CLAWTEAM_DATA_DIR). Agents coordinate via the shared filesystem: kanban tasks, per-recipient inboxes, team configs, git worktree registries.
Common commands
# Dev install (from repo root)
pip install -e ".[dev]" # dev deps: pytest, ruff
pip install -e ".[p2p]" # optional ZeroMQ P2P transport
# Lint + test — same commands CI runs (.github/workflows/ci.yml)
ruff check clawteam/ tests/
pytest tests/ # full suite
pytest tests/test_spawn_backends.py -v # one file
pytest tests/test_board.py::test_foo -v # one test
pytest -k "mailbox" # by name
# CLI entry points
clawteam <subcommand> # installed script
python -m clawteam <subcommand> # module entry (clawteam/__main__.py)
Tests auto-isolate: tests/conftest.py monkeypatches both CLAWTEAM_DATA_DIR and HOME to tmp_path, so no test can touch real ~/.clawteam/ or ~/.clawteam/config.json.
Architecture — the big picture
CLI surface
All commands live in a single file: clawteam/cli/commands.py (~2700 lines). It uses typer sub-apps:
| Sub-app | Purpose |
|---|---|
config |
show / set / get / health |
team |
spawn-team / discover / status / request-join / approve-join / cleanup |
inbox |
send / broadcast / receive / peek / log / watch |
task |
create / get / update / list / stats / wait |
cost |
report / show / budget |
session |
save / show / clear |
plan |
submit / approve / reject |
lifecycle |
request-shutdown / approve-shutdown / idle / on-exit / check-zombies |
runtime |
tmux-only live injection: inject / watch / state |
identity |
show / set |
board |
show / overview / live / serve (web UI) / attach (tmux tiled view) |
workspace |
list / checkpoint / merge / cleanup / status |
template |
list / show |
| (top-level) | spawn and launch |
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.
- 7d ago First seen · 171 lines · 3,463 tokens per session scan A 995441193d3f
ClawTeam-OpenClaw CLAUDE.md is an instructions file published in the GitHub repository win4r/ClawTeam-OpenClaw (1,448 stars, last pushed 2mo ago), licensed MIT. It adds 3,463 tokens to every session, about $0.0173 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
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.
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.
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).
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).
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.
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.