ClawTeam is a command-line system for forming swarms of AI agents that can divide work, coordinate tasks, and deliver results from a human-provided goal. It is designed for agent-based research, software development, business operations, content production, and other multi-agent workflows.
Borrowing it
Nothing to install: this file belongs to HKUDS/ClawTeam. 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/HKUDS/ClawTeam/main/.agents/skills/clawteam-dev/SKILL.mdgit clone --depth 1 https://github.com/HKUDS/ClawTeamWrote 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/skills/hkuds/clawteam/clawteam-dev)<a href="https://agentmods.dev/skills/hkuds/clawteam/clawteam-dev"><img src="https://agentmods.dev/badge/skills/hkuds/clawteam/clawteam-dev/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.
<a href="https://agentmods.dev/skills/hkuds/clawteam/clawteam-dev"><img src="https://agentmods.dev/badge/skills/hkuds/clawteam/clawteam-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.01016 |
| Opus 5.5 | $0.00038 | $0.00406 |
| Sonnet 5.5 | $0.00019 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
clawteam-dev 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- clawteam-dev — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawTeam Local Development
This skill is for developing and validating ClawTeam inside the ClawTeam repository. Use it when the task is about changing ClawTeam itself, testing local behavior, or verifying multi-agent workflows against the current checkout.
Development Bootstrap
Standardize the local development environment with the bootstrap script:
bash scripts/bootstrap_clawteam_dev.sh
This script lives in scripts/bootstrap_clawteam_dev.sh inside this skill folder.
This script does all of the following:
- Creates a fixed uv environment at
~/.clawteam-venv - Installs the current repository into that environment with dev dependencies
- Writes
~/.local/bin/clawteamto point at the fixed environment - Adds a
clawteam()shell function block to~/.bashrc
After it finishes:
source ~/.bashrc
clawteam --version
Use this bootstrap whenever you want the same clawteam command across different
Python environments on the machine.
Project Skill Wiring
To wire another local project so its ./.agents and ./.claude directories use
this repository's local ClawTeam skills directly:
bash scripts/link_local_clawteam_skills.sh /path/to/project
This script lives in scripts/link_local_clawteam_skills.sh inside this skill folder.
This creates these symlinks inside the target project:
./.agents/skills/clawteam./.claude/skills/clawteam
Run the same script again any time you want to refresh or recreate those links.
Typical Uses
- Run targeted local validation after code changes
- Reproduce a spawn / board / task / inbox / harness bug
- Smoke-test the real CLI in tmux or subprocess mode
- Review ClawTeam workflows end-to-end from the current repository checkout
Fast Validation
Prefer the smallest validation that proves the change.
ruff check clawteam/ tests/
pytest tests/<target_file>.py -q
Use broader runs only when the change crosses modules:
pytest tests/test_cli_commands.py -q
pytest tests/test_spawn_backends.py -q
pytest tests/test_harness.py tests/test_event_bus.py -q
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 134 lines · 94 tokens per session scan A 84504f03ffc1
clawteam-dev is a skill published in the GitHub repository HKUDS/ClawTeam (5,538 stars, last pushed 5mo ago), licensed MIT. It adds 94 tokens to every session and 1,016 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…