teamwork

teamwork is a command for Claude Code from mnthe/hardworker-marketplace. It costs 12 tokens per session (887 once invoked), scanned A, original, MIT.

A command for starting a teamwork project in which an orchestrating agent coordinates other agents through a shared project lifecycle. It can optionally activate Serena, a tool for navigating code by its symbols.

In plain words
What is it for?
Use it to initialize and coordinate multi-agent coding projects, including project setup, worker coordination, and later verification.
Why use it?
It provides a defined way to set up agent collaboration and divide project work. The optional code-navigation support can help agents locate relevant functions and structures more precisely.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the teamwork plugin — 4 skills, 5 commands shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add mnthe/hardworker-marketplace
Claude Code
/plugin install teamwork

Made for: Claude Code.

Or install teamwork, the plugin that ships this one along with the rest of its 4 skills, 5 commands.

Wrote 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.

agentmods badge for teamwork

README.md
[![agentmods](https://agentmods.dev/badge/commands/mnthe/hardworker-marketplace/teamwork.svg)](https://agentmods.dev/commands/mnthe/hardworker-marketplace/teamwork)
Your own site
<a href="https://agentmods.dev/commands/mnthe/hardworker-marketplace/teamwork"><img src="https://agentmods.dev/badge/commands/mnthe/hardworker-marketplace/teamwork.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 887 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00012 $0.00887
Opus 5 $0.00006 $0.00443
Sonnet 5 $0.00002 $0.00177
Haiku 4.5 $0.00001 $0.00089

Measured 6d ago against content hash e4a46bcffac3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

teamwork 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 6d 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.

plugins/teamwork/commands/teamwork.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teamwork Command

Overview

Teamwork enables native agent team collaboration. An orchestrator (team lead) handles the full project lifecycle: planning, spawning workers, coordination, and verification -- all through Claude's native teammate API.


Step 0: Serena Project Activation (Optional)

If the MCP tool mcp__plugin_serena_serena__activate_project is available, activate Serena for enhanced code navigation:

# Check if Serena is available and activate
if "mcp__plugin_serena_serena__activate_project" in available_tools:
    try:
        mcp__plugin_serena_serena__activate_project(project=".")
        # Serena enabled - agents can use symbol-based tools
    except:
        pass  # Continue without Serena

Benefits when Serena is active:

  • Orchestrator: get_symbols_overview, find_symbol for precise code structure analysis
  • Workers: Symbol-based editing tools for safe refactoring

If Serena is not available, agents will use standard tools (Read, Edit, Grep).


Step 1: Initialize Project

Execute the setup script:

bun "${CLAUDE_PLUGIN_ROOT}/src/scripts/setup-teamwork.js" $ARGUMENTS

This initializes project metadata and validates the environment (including CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1).

Parse the output to get:

  • Project name
  • Sub-team name
  • Teamwork directory path
  • Goal

Step 2: Spawn Orchestrator

The orchestrator is the team lead. It handles the full project lifecycle:

  1. Explore the codebase
  2. Create tasks with dependencies (TaskCreate + addBlockedBy)
  3. Spawn worker teammates (Task with team_name)
  4. Coordinate via SendMessage
  5. Monitor progress via TaskList
  6. Trigger final verification
  7. Report project completion

ACTION REQUIRED - Call Task tool with:

  • subagent_type: "teamwork:orchestrator"
  • model: "opus"
  • prompt:
    TEAMWORK_DIR: {teamwork_dir}
    PROJECT: {project}
    SUB_TEAM: {sub_team}
    SCRIPTS_PATH: ${CLAUDE_PLUGIN_ROOT}/src/scripts
    
    Goal: {goal}
    

Read the full file on GitHub · 138 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. 6d ago First seen · 138 lines · 12 tokens per session scan A e4a46bcffac3

Subscribe to this mod's changes

teamwork is a command published in the GitHub repository mnthe/hardworker-marketplace (4 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 887 once invoked, about $0.0001 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.