Dev & Engineering multi-agent-orchestrationswarm-coordinationgit-worktreetmuxtask-dependencieskanbanopenclawcli-agents

ClawTeam Multi-Agent Swarm Coordination

Turn CLI coding agents into self-organizing teams that split tasks, work in parallel, manage dependencies, message each other, and merge results — one command to launch.

FollowSkills review · FSRS-2.0
Use with care
49/ 100 5-point scale 2.5 / 5
1 2 3 4 5 6
1Trust12 / 25 · 2.4/5

Docs transparently disclose data locations (~/.clawteam), spawn safety (pre-validation, rollback) and exec-approvals config; but the skill auto-confirms workspace trust prompts, recommends allowlist reconfiguration and uses --force cleanup with broad external effects and no per-action user confirmation — deducted.

2Reliability8 / 20 · 2.0/5

SKILL.md command tables are self-consistent with troubleshooting and rollback notes; CI and adapter tests exist, but tests do not cover this skill's key paths (team lifecycle, messaging, merging); failure-feedback quality is asserted only — unverified in static review, deducted.

3Adaptability9 / 15 · 3.0/5

Clear trigger phrases, scenarios and boundaries (tmux dependency, Windows fallback); multilingual README helps Chinese users; but core dependence on OpenClaw/external CLIs and a GitHub install path, with mainland-China reachability undeclared and non-fit ranges thinly disclosed, deducted.

4Convention11 / 15 · 3.7/5

Well-layered docs, clear versioning (0.3.0+openclaw2), MIT license, explicit upstream attribution; but no changelog, maintenance/update path only implicit in the fork claim, and the npm name-squatting warning reveals naming risk, deducted.

5Effectiveness5 / 15 · 1.7/5

The orchestration value proposition is concrete with a complete workflow, but all effect claims (e.g. the 8-GPU research case via an external repo) are statically unverifiable, with no representative usable-output evidence and thin comparative-benefit data, deducted.

6Verifiability4 / 10 · 2.0/5

CI workflow plus committed tests (good adapter coverage) exist, but tests do not directly exercise this skill's key paths; effectiveness claims lean on external links and marketing-style narrative without strict fact/inference separation, deducted.

Evidence confidence:Low Reviewed Sep 09, 2026 Reviewed revision 8dac3fc9774d
Before you use it
  • The skill auto-confirms workspace trust prompts and suggests rewriting exec-approvals config; manually review allowlist changes before installing.
  • clawteam team cleanup --force irreversibly deletes all team data; save results before use.
  • No tests found covering the openclaw skill path itself; rehearse on a small team first.
  • Depends on OpenClaw and other external services plus a GitHub install path; mainland-China reachability is undeclared — verify independently.
  • Publisher is unverified and an npm name-squatting package exists; install from the local repository per the README only.
Review evidence [1][2][3][4][5][6][7][8]
See the full review method →

What does this skill do, and when should you use it?

ClawTeam is a CLI tool (clawteam) that orchestrates multiple AI coding agents as self-organizing swarms. It isolates each agent in its own git worktree, hosts sessions in tmux windows, and routes communication through filesystem-based inboxes. This skill (skills/openclaw/SKILL.md) teaches an OpenClaw agent to create teams, spawn workers, manage task dependencies, and monitor progress via natural language. The repository is a fork of HKUDS/ClawTeam deeply adapted to make OpenClaw the default agent backend. Three pre-built team templates ship out of the box: hedge-fund, code-review, and research-paper.

When the user expresses intent like 'build a team', 'spawn agents', or 'swarm', the skill guides the agent to: create a team with a leader via clawteam team spawn-team; build dependency chains with clawteam task create --blocked-by (dependents auto-unblock when blockers complete); give each worker its own tmux window plus a git worktree on branch clawteam/{team}/{agent} with an auto-injected coordination prompt via clawteam spawn; exchange point-to-point and broadcast messages via inbox send/broadcast/receive; monitor via board show/attach/serve (terminal kanban, tiled tmux view, or Web dashboard); track spend with cost report/show/budget; merge branches with workspace merge and tear down with team cleanup. All state lives as JSON files under ~/.clawteam/ with fcntl file locking for concurrent safety, and every command supports -- output.

  1. Full-stack development: say 'create a team to build a web app with auth' — the leader splits work into a dependency chain (API design → backend/frontend → tests), 5 agents develop in parallel in separate worktrees, then everything merges to main
  2. Investment analysis: clawteam launch hedge-fund boots a 7-agent team (5 parallel analysts, a risk manager, and a portfolio manager) from a single TOML template
  3. Code review: launch the code-review template so multiple agents divide up review work and consolidate findings
  4. Research writing: launch the research-paper template to organize literature survey and writing assignments
  5. Large-scale experimentation: a leader spawns multiple research agents in isolated worktrees and cross-pollinates best configs (README cites an autoresearch run: 2,430 experiments in ~30 GPU-hours)

What are this skill's strengths and limitations?

Pros
  • Agent self-organization: coordination logic runs in the leader agent — no human-written orchestration code
  • Real isolation: each agent works on its own git worktree branch, avoiding parallel-edit conflicts, with merge support on completion
  • Zero infrastructure: filesystem + tmux only; state is JSON under ~/.clawteam/, no database or message queue needed
  • Automatic dependency resolution, task locking against double-claims, and auto-release of stale locks from dead agents
  • Multiple monitoring options: terminal kanban, tiled tmux view, Web dashboard, and -- output on all commands
  • Spawn safety: pre-validation of commands, automatic rollback on failed spawns, auto-confirmed trust prompts for Claude Code/Codex worktrees
Limitations
  • Installation is multi-step and manual: PATH symlink, exec-approval configuration, and skill file copying
  • Strong local-environment dependency: Python 3.10+, git, tmux (Linux/macOS) and at least one CLI agent — not usable in pure cloud-API setups as-is
  • board attach requires tmux and is unavailable on native Windows (README suggests board serve or WSL instead)
  • No automated test suite or benchmark data appears in SKILL.md or README; some claimed results (e.g., the 8-GPU experiment) are external case studies cited from elsewhere, not verified in this repo
  • Switching the spawn backend away from openclaw (e.g., to claude) hits interactive permission prompts unless extra configuration is done

How do you install this skill?

Prerequisites: Python 3.10+, git, tmux on Linux/macOS, and at least one CLI coding agent (OpenClaw by default). Do NOT pip install clawteam (that's the upstream version defaulting to claude, without OpenClaw adaptations) and do NOT npm install -g clawteam (an unrelated name-squatting package). Correct install:

  1. git clone https://github.com/win4r/ClawTeam-OpenClaw.git && cd ClawTeam-OpenClaw
  2. pip install -e . (required — installs from the local repo, not PyPI)
  3. Ensure clawteam is on PATH: mkdir -p ~/bin && ln -sf "$(which clawteam)" ~/bin/clawteam
  4. Install this skill: mkdir -p ~/.openclaw/workspace/skills/clawteam && cp skills/openclaw/SKILL.md ~/.openclaw/workspace/skills/clawteam/SKILL.md
  5. Set OpenClaw exec approvals to 'allowlist' and add the absolute clawteam path to the allowlist (scripts included in the skill). Alternatively run bash scripts/install-openclaw.sh to automate.

How do you use this skill?

After installation, just talk to your OpenClaw agent in natural language — trigger phrases include team, swarm, multi-agent, spawn agents. Example: 'Create a 5-agent team to build a web app' — the agent creates the team, tasks, and workers and starts a background monitoring loop automatically. Manual route: clawteam launch hedge-fund --team fund1 for one-command template launch, or step through team spawn-team → task create → spawn → board serve. Important: keep the default openclaw spawn command; overriding to claude will get agents stuck on interactive permission prompts.

How does this skill compare with similar options?

The README contrasts ClawTeam with other multi-agent frameworks: those require Docker, cloud APIs, YAML configs, Redis/message queues, are driven by humans writing orchestration code, and are framework-agent-specific. ClawTeam needs only pip install plus one prompt, uses filesystem + tmux as infrastructure, accepts any CLI agent, and isolates via real git worktrees. The upstream HKUDS/ClawTeam defaults to claude and lacks OpenClaw adaptations; this fork is the deeply OpenClaw-integrated version.

FAQ

How much does running this skill cost?
Cost scales with how many agents you spawn and how long they run. ClawTeam ships cost report/show/budget commands that track token usage and spend per team with budget caps; the skill's wrap-up flow requires reporting cost stats alongside deliverables.
How do agents avoid editing the same files?
Every spawned agent gets its own git worktree on branch clawteam/{team}/{agent}, works in isolation, and the leader merges each branch back to main with workspace merge when tasks complete.
What happens if an agent gets stuck or a spawn fails?
Tasks use an in_progress lock; stale locks from dead agents are auto-released. Failed spawns roll back the registered member and worktree automatically. The leader orchestration pattern mandates proactive inbox checks, nudges to stalled workers, and final merge-and-cleanup.
Can I use this without OpenClaw?
Yes. OpenClaw is the default backend, but the README lists full support for Claude Code, Codex, nanobot, and Hermes Agent, plus experimental Cursor support. Note that this particular skill file targets OpenClaw's install and approval flow, and non-openclaw backends like claude may hit interactive permission prompts without extra setup.

More skills from this repository

All from win4r/ClawTeam-OpenClaw

Related skills