New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

ClawTeam Multi-Agent Swarm

by win4r in win4r/ClawTeam-OpenClaw

Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review.

MITAuto-check passedAgent Workflows

Install ClawTeam Multi-Agent Swarm

skills CLI
$ npx skills add win4r/ClawTeam-OpenClaw --skill clawteam -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install win4r/ClawTeam-OpenClaw clawteam --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/win4r/ClawTeam-OpenClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openclaw .claude/skills/clawteam && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
clawteam
GitHub stars
1.5k
Used in
1 other repo
Token cost
~2.9k tokens
SKILL.md length
884 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review.

  • Works in 5 steps: Analyze & Plan → Setup → Spawn Workers → …
  • Getting multi-perspective analysis of a stock, codebase or strategy question
  • SKILL.md covers Overview, Quick Start, Command Reference and JSON Output, plus 3 more sections
  • Calls python3

What it does

The skill applies instead of a single delegate_task call whenever the user asks for a team, swarm, multi-agent or parallel-agent treatment, or wants multi-perspective analysis such as stock analysis, research across sources, multi-angle code review or strategy brainstorming, since delegate_task spawns only one sub-agent while this runs five to seven specialists in parallel. Launching a built-in template needs a command flag pointing at hermes, because templates default to a different agent and otherwise fail with gateway token errors, and a force flag suppresses the max-agent warning; manual spawning instead takes a team name, an agent name and a task string.

Four templates are named: hedge-fund with seven analyst agents covering portfolio management, a value-investing style, growth, technical, fundamentals, sentiment and risk, plus research-paper, code-review and strategy-room. Spawned workers take 20 to 40 seconds to boot while loading their tools, skills and MCP servers, then one to five minutes to produce output, so the skill warns against checking inboxes within the first 60 seconds and against cleaning a team up early.

When your agent uses it

  • Getting multi-perspective analysis of a stock, codebase or strategy question
  • Running a code review from several specialist angles at once
  • Launching a swarm of parallel agents instead of one sub-agent

Example prompts

  • “Use the hedge-fund template to analyze TSLA from seven angles.”
  • “Spin up a code-review swarm session on this pull request.”
  • “Launch a strategy-room swarm to brainstorm our Q1 pricing options.”

Requirements

  • tmux
  • git worktree support
  • The clawteam CLI configured for Hermes

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Analyze & Plan
  2. Setup
  3. Spawn Workers
  4. Monitor Loop
  5. Converge & Report

What it can do on your machine

Read from SKILL.md and the folder at commit 8dac3fc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

ClawTeam Multi-Agent Swarm loads about 2.9k tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 884 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from win4r/ClawTeam-OpenClaw at commit 8dac3fc, republished under its MIT licence (© win4r). 884 words, ~2,913 tokens.

Download SKILL.mdSave it as .claude/skills/clawteam/SKILL.md (or your agent's skills folder).
name
clawteam
description
Multi-agent swarm coordination via the ClawTeam CLI. Use when the user wants to create agent teams, spawn multiple agents to work in parallel, coordinate tasks with dependencies, broadcast messages between agents, monitor progress via kanban board, or launch pre-built team templates (hedge-fund, code-review, research-paper). ClawTeam uses git worktree isolation + tmux + filesystem-based messaging. Trigger phrases: team, swarm, multi-agent, clawteam, spawn agents, parallel agents, agent team.

ClawTeam — Multi-Agent Swarm Coordination

Overview

ClawTeam is a CLI tool (clawteam) for orchestrating multiple AI agents as self-organizing swarms. It uses git worktree isolation, tmux windows, and filesystem-based messaging. OpenClaw is the default agent backend.

CLI binary: clawteam (installed via pip, available in PATH)

Quick Start

bash
# Launch a pre-built team from a template
clawteam launch hedge-fund --team fund1
clawteam launch code-review --team review1
clawteam launch research-paper --team paper1
Manual Team Setup
bash
# 1. Create team with leader
clawteam team spawn-team my-team -d "Build a web app" -n leader

# 2. Create tasks with dependencies
clawteam task create my-team "Design API schema" -o architect
# Returns task ID, e.g., abc123

clawteam task create my-team "Implement auth" -o backend --blocked-by abc123
clawteam task create my-team "Build frontend" -o frontend --blocked-by abc123
clawteam task create my-team "Write tests" -o tester

# 3. Spawn agents (each gets its own tmux window + git worktree)
clawteam spawn -t my-team -n architect --task "Design the API schema for a web app"
clawteam spawn -t my-team -n backend --task "Implement OAuth2 authentication"
clawteam spawn -t my-team -n frontend --task "Build React dashboard"

# 4. Monitor
clawteam board show my-team        # Kanban view
clawteam board attach my-team      # Tmux tiled view (all agents side-by-side)
clawteam board serve --port 8080   # Web dashboard

Command Reference

Team Management
CommandDescription
clawteam team spawn-team <name> -d "<desc>" -n <leader>Create team
clawteam team discoverList all teams
clawteam team status <team>Show team members and info
clawteam team cleanup <team> --forceDelete team and all data
Task Management
CommandDescription
clawteam task create <team> "<subject>" -o <owner> [-d "<desc>"] [--blocked-by <id>]Create task
clawteam task list <team> [--owner <name>]List tasks (filterable)
clawteam task update <team> <id> --status <status>Update status
clawteam task get <team> <id>Get single task
clawteam task stats <team>Timing statistics
clawteam task wait <team>Block until all tasks complete

Task statuses: pending, in_progress, completed, blocked

Dependency auto-resolution: When a blocking task completes, dependent tasks automatically change from blocked to pending.

Task locking: When a task moves to in_progress, it is locked by the calling agent. Other agents cannot claim it unless they use --force. Stale locks from dead agents are automatically released.

Agent Spawning

IMPORTANT: Always use the default command (openclaw) — do NOT override to claude or other agents. The default handles permissions, prompt injection, and nesting detection correctly. If you specify claude as the command, agents will get stuck on interactive permission prompts.

bash
# Default (RECOMMENDED): spawns openclaw tui in tmux with prompt
clawteam spawn -t <team> -n <name> --task "<task description>"

# Explicit backend (still uses openclaw by default)
clawteam spawn tmux -t <team> -n <name> --task "<task>"
clawteam spawn subprocess -t <team> -n <name> --task "<task>"

# With git worktree isolation
clawteam spawn -t <team> -n <name> --task "<task>" --workspace --repo /path/to/repo

Each spawned agent gets:

  • Its own tmux window (visible via board attach)
  • Its own git worktree branch (clawteam/{team}/{agent})
  • An auto-injected coordination prompt (how to use clawteam CLI)
  • Environment variables: CLAWTEAM_AGENT_NAME, CLAWTEAM_TEAM_NAME, etc.

Spawn safety features:

  • Commands are pre-validated before launch — you get a clear error if the agent CLI is not installed
  • If a spawn fails, the registered team member and worktree are automatically rolled back
  • Claude Code and Codex workspace trust prompts are auto-confirmed in fresh worktrees
Messaging
CommandDescription
clawteam inbox send <team> <to> "<msg>" --from <sender>Point-to-point message
clawteam inbox broadcast <team> "<msg>" --from <sender>Broadcast to all
clawteam inbox peek <team> -a <agent>Peek without consuming
clawteam inbox receive <team>Consume messages
clawteam inbox log <team>View message history
Monitoring
CommandDescription
clawteam board show <team>Kanban board (rich terminal)
clawteam board overviewAll teams overview
clawteam board live <team>Live-refreshing board
clawteam board attach <team>Tmux tiled view
clawteam board serve --port 8080Web dashboard
Cost Tracking
CommandDescription
clawteam cost report <team> --input-tokens <N> --output-tokens <N> --cost-cents <N>Report usage
clawteam cost show <team>Show summary
clawteam cost budget <team> <dollars>Set budget
Templates
CommandDescription
clawteam template listList available templates
clawteam template show <name>Show template details
clawteam launch <template> [--team-name <name>] [--goal "<goal>"]Launch from template

Built-in templates: hedge-fund, code-review, research-paper

Configuration
bash
clawteam config show                           # Show all settings
clawteam config set transport file             # Set transport backend
clawteam config set skip_permissions true      # Auto-skip permission prompts
clawteam config health                         # System health check
Other Commands
CommandDescription
clawteam lifecycle idle <team> --agent <name>Report agent idle
clawteam session save <team> --session-id <id>Save session for resume
clawteam plan submit <team> "<plan>" --from <agent>Submit plan for approval (team-scoped storage)
clawteam workspace list <team>List git worktrees
clawteam workspace merge <team> --agent <name>Merge agent branch

JSON Output

Add --json before any subcommand for machine-readable output:

bash
clawteam --json task list my-team
clawteam --json team status my-team
Show full SKILL.md (354 more words)Show less

Typical Workflow

  1. User says: "Create a team to build a web app"
  2. You do: clawteam team spawn-team webapp -d "Build web app" -n leader
  3. Create tasks: Use clawteam task create with --blocked-by for dependencies
  4. Spawn agents: Use clawteam spawn for each worker
  5. Monitor: Start a background polling loop immediately — do NOT wait for user to ask
  6. Communicate: Use clawteam inbox broadcast for team-wide updates
  7. Deliver: Proactively send final results to the user as soon as all tasks complete
  8. Cleanup: clawteam cost show, clawteam task stats, merge worktrees, then clawteam team cleanup webapp --force

Leader Orchestration Pattern

When YOU are the leader agent, follow this pattern to autonomously manage a swarm:

Phase 1: Analyze & Plan
1. Understand the user's goal
2. Break it into independent subtasks
3. Identify dependencies between tasks (what must finish before what)
4. Decide how many worker agents are needed
Phase 2: Setup
bash
# Create team
clawteam team spawn-team <team> -d "<goal description>" -n leader

# Create tasks with dependency chains
clawteam task create <team> "Design API" -o architect
# Save the returned task ID (e.g., abc123)
clawteam task create <team> "Build backend" -o backend --blocked-by abc123
clawteam task create <team> "Build frontend" -o frontend --blocked-by abc123
clawteam task create <team> "Integration tests" -o tester --blocked-by <backend-id>,<frontend-id>
Phase 3: Spawn Workers
bash
# Each spawn launches an openclaw tui in its own tmux window
clawteam spawn -t <team> -n architect --task "Design REST API schema for <goal>"
clawteam spawn -t <team> -n backend --task "Implement backend based on API schema"
clawteam spawn -t <team> -n frontend --task "Build React frontend"
clawteam spawn -t <team> -n tester --task "Write and run integration tests"
Phase 4: Monitor Loop

IMPORTANT: Start monitoring immediately after spawning — do NOT wait for the user to ask for status updates. Run the monitor loop in the background right away so you can:

  1. Push mid-progress updates proactively — when ~50% of tasks complete, send the user a brief status update (e.g. "4/7 agents done, 3 still working"). Do NOT wait for them to ask.
  2. Deliver final results immediately when all tasks complete.
bash
# Poll task status every 30-60 seconds
while true; do
  clawteam --json task list <team> | python3 -c "
import sys, json
tasks = json.load(sys.stdin)
done = sum(1 for t in tasks if t['status'] == 'completed')
total = len(tasks)
print(f'{done}/{total} complete')
if done == total: print('ALL DONE'); sys.exit(0)
"
  # Check for messages from workers
  clawteam inbox receive <team>
  # IMPORTANT: Send a mid-progress update to the user when roughly half the tasks are done
  sleep 30
done
Phase 5: Converge & Report

IMPORTANT: Proactively deliver results to the user as soon as all tasks complete. Do NOT wait for the user to ask. Include the final output, a summary, and cost/timing stats. ALWAYS merge worktrees and clean up.

bash
# After all tasks complete — do ALL of these steps:
clawteam board show <team>           # Final status
clawteam cost show <team>            # Total cost — include in report to user
clawteam task stats <team>           # Timing stats — include in report to user
# Merge each worker's branch back to main
for agent in <agent1> <agent2> ...; do
  clawteam workspace merge <team> --agent $agent
done
clawteam team cleanup <team> --force  # Clean up — ALWAYS do this last
# Then: send the final deliverables to the user immediately
Decision Rules for the Leader
  • Independent tasks → spawn workers in parallel
  • Sequential tasks → use --blocked-by to chain them; ClawTeam auto-unblocks
  • Worker asks for help → check inbox, provide guidance via inbox send
  • Worker stuck → check task status; if in_progress too long, send a nudge via inbox send
  • Worker done → verify result via inbox message, then move to next phase
  • All done → merge worktrees, deliver results to user proactively, then cleanup
  • Always → start background monitoring immediately after spawn; never wait for user to ask for status

Data Location

All state stored in ~/.clawteam/:

  • Teams: ~/.clawteam/teams/<team>/config.json
  • Tasks: ~/.clawteam/tasks/<team>/task-<id>.json (with fcntl file locking for concurrent safety)
  • Plans: ~/.clawteam/plans/<team>/<agent>-<plan_id>.md (team-scoped, isolated per team)
  • Messages: ~/.clawteam/teams/<team>/inboxes/<agent>/msg-*.json
  • Costs: ~/.clawteam/costs/<team>/

© win4r, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/openclaw of win4r/ClawTeam-OpenClaw.

Open the folder on GitHubat commit 8dac3fc

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in win4r/ClawTeam-OpenClaw, which our catalogue first saw on October 7, 2026.

Compare with similar skills

ClawTeam Multi-Agent Swarm next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

ClawTeam Multi-Agent Swarm compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
ClawTeam Multi-Agent Swarm this skillwin4r/ClawTeam-OpenClaw1.5k1 repos~2.9kAutomated safety check: PassMIT
Puppetmaster Agent Orchestrationprofessorpalmer/Puppetmaster467—~3.2kAutomated safety check: PassMIT
Qwen Code Team CoordinatorQwenLM/qwen-code28k—~994Automated safety check: PassApache-2.0
Agenthubalirezarezvani/claude-skills28k—~2kAutomated safety check: PassMIT
O2 Review Loopopenobserve/openobserve22k—~3.7kAutomated safety check: PassAGPL-3.0
Agent Deckasheshgoplani/agent-deck1k—~1.7kAutomated safety check: PassMIT

Similar skills

  • Puppetmaster Agent Orchestration

    professorpalmer/Puppetmaster

    Operates and supervises Puppetmaster, a multi-agent orchestrator, through its MCP tools or CLI, picking the right verb for edits, reviews, audits and long-running jobs.

    467 GitHub stars~3.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Qwen Code Team Coordinator

    QwenLM/qwen-code

    Leads a small team of Qwen Code teammates: read-only investigators work in parallel, then one writer pinned to a git worktree makes the changes.

    28k GitHub stars~994 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Agenthub

    alirezarezvani/claude-skills

    Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation.

    28k GitHub stars~2k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Agent Deck

    asheshgoplani/agent-deck

    agent-deck, the terminal session manager for AI coding agents.

    1k GitHub stars~1.7k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

  • Huashu Agent Swarm

    alchaincyf/huashu-skills

    多Agent蜂群并行协作，纯git自组织，适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。

    1.7k GitHub stars~576 tokensUpdated 17 days ago
    Agent WorkflowsAuto-check passed

More from win4r/ClawTeam-OpenClaw

  • Clawteam

    win4r/ClawTeam-OpenClaw

    Multi-agent swarm orchestration. An agent skill from win4r/ClawTeam-OpenClaw.

    1.5k GitHub stars~3.1k tokensUpdated 3 mo ago
    Auto-check passed

Works with

Categories

Questions about ClawTeam Multi-Agent Swarm

What does ClawTeam Multi-Agent Swarm do?

Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review. The skill applies instead of a single delegate_task call whenever the user asks for a team, swarm, multi-agent or parallel-agent treatment, or wants multi-perspective analysis such as stock analysis, research across sources, multi-angle code review or strategy brainstorming, since delegate_task spawns only one sub-agent while this runs five to seven specialists in parallel. Launching a built-in template needs a command flag pointing at hermes, because templates default to a different agent and otherwise fail with gateway token errors, and a force flag suppresses the max-agent warning; manual spawning instead takes a team name, an agent name and a task string.

When should I use ClawTeam Multi-Agent Swarm?

ClawTeam Multi-Agent Swarm fits situations like: getting multi-perspective analysis of a stock, codebase or strategy question; running a code review from several specialist angles at once; launching a swarm of parallel agents instead of one sub-agent.

How do I install ClawTeam Multi-Agent Swarm in Claude Code?

Run `npx skills add win4r/ClawTeam-OpenClaw --skill clawteam -a claude-code`. Or copy the skill folder (skills/openclaw in win4r/ClawTeam-OpenClaw) into .claude/skills/clawteam in your project. Claude Code loads it when a task matches its description.

How do I install ClawTeam Multi-Agent Swarm in Codex?

Run `npx skills add win4r/ClawTeam-OpenClaw --skill clawteam -a codex`. Or copy the skill folder (skills/openclaw in win4r/ClawTeam-OpenClaw) into .agents/skills/clawteam in your project. Codex loads it when a task matches its description.

Can I use ClawTeam Multi-Agent Swarm in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add win4r/ClawTeam-OpenClaw --skill clawteam -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clawteam, .gemini/skills/clawteam, .github/skills/clawteam and .opencode/skills/clawteam in your project.

What does ClawTeam Multi-Agent Swarm need to run?

Going by SKILL.md and its folder, ClawTeam Multi-Agent Swarm needs the command-line tools its instructions call (python3). Our summary lists: tmux; git worktree support; The clawteam CLI configured for Hermes.

Does ClawTeam Multi-Agent Swarm access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is ClawTeam Multi-Agent Swarm safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does ClawTeam Multi-Agent Swarm use?

ClawTeam Multi-Agent Swarm is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does ClawTeam Multi-Agent Swarm use?

About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to ClawTeam Multi-Agent Swarm?

Skills that share tags, products or a category with ClawTeam Multi-Agent Swarm: Puppetmaster Agent Orchestration (professorpalmer/Puppetmaster, 467 stars), Qwen Code Team Coordinator (QwenLM/qwen-code, 28k stars), Agenthub (alirezarezvani/claude-skills, 28k stars) and O2 Review Loop (openobserve/openobserve, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains ClawTeam Multi-Agent Swarm?

win4r (a GitHub user) maintains it in win4r/ClawTeam-OpenClaw, which has 1,461 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on July 3, 2026.

Source: win4r/ClawTeam-OpenClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.