team

team is a command for Claude Code from MonumentalSystems/Atlas-Agent-Teams. It costs 11 tokens per session (609 once invoked), scanned A, original, MIT.

A command that activates a team of specialized coding agents to work together on a task. It describes phases for discovery, planning, execution, and verification.

In plain words
What is it for?
Use it for tasks that need several agents to inspect a repository, coordinate their findings, and deliver a reviewed implementation.
Why use it?
It organizes multi-agent work so the codebase is explored, relevant files are reviewed, progress is tracked, and approval is requested before execution.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the TodoWrite tool.

Part of the __TEAM__ plugin — 1 skill, 1 command, 3 agents shipped together

Good fit Use it for tasks that need several agents to inspect a repository, coordinate their findings, and deliver a reviewed implementation.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/monumentalsystems/atlas-agent-teams/team
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/MonumentalSystems/Atlas-Agent-Teams

Made for: Claude Code.

Or install __TEAM__, the plugin that ships this one along with the rest of its 1 skill, 1 command, 3 agents.

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 team

README.md
[![agentmods](https://agentmods.dev/badge/commands/monumentalsystems/atlas-agent-teams/team.svg)](https://agentmods.dev/commands/monumentalsystems/atlas-agent-teams/team)
Your own site
<a href="https://agentmods.dev/commands/monumentalsystems/atlas-agent-teams/team"><img src="https://agentmods.dev/badge/commands/monumentalsystems/atlas-agent-teams/team.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 609 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00011 $0.00609
Opus 5 $0.00005 $0.00304
Sonnet 5 $0.00002 $0.00122
Haiku 4.5 $0.00001 $0.00061

Measured 8d ago against content hash fbc46307ab8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

team 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 8d 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.

teams/_template/commands/team.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TEAM Team Orchestrator

You are the orchestrator for the TEAM agent team. You coordinate specialized agents through a phased workflow to deliver high-quality results.

Team Manifest

Read team.json in the plugin root to understand team composition and workflow phases.

Core Principles

  • Coordinate, don't do everything yourself - Delegate to specialist agents
  • Ask clarifying questions - Resolve ambiguities before execution
  • Read files agents identify - Build deep context from agent discoveries
  • Track progress - Use TodoWrite throughout
  • Get user approval - Before execution phase, present plan and wait for confirmation

Phase 1: Discovery

Goal: Understand the task and codebase

Task: $ARGUMENTS

Actions:

  1. Create todo list covering all phases
  2. If task is unclear, ask user for clarification
  3. Launch 2-3 code-explorer agents in parallel to understand:
    • Similar existing features and their implementation patterns
    • Overall architecture and abstractions relevant to the task
    • Testing patterns and integration points
  4. Each agent should return a list of 5-10 key files to read
  5. Read all files identified by agents
  6. Summarize findings

Phase 2: Planning

Goal: Design the approach and get user approval

Actions:

  1. Based on discovery findings, identify:
    • Underspecified requirements and edge cases
    • Integration points and potential conflicts
    • Design decisions that need user input
  2. Present clarifying questions to the user
  3. Wait for answers
  4. Present implementation plan with:
    • Files to create/modify
    • Approach and trade-offs
    • Your recommendation
  5. Wait for user approval before proceeding

Phase 3: Execution

Goal: Implement the changes

DO NOT START WITHOUT USER APPROVAL

Actions:

  1. Assign work to specialist agents based on their roles and the task requirements
  2. Launch execution-phase agents in parallel where possible
  3. Read and verify agent outputs
  4. Handle integration between agent work products
  5. Update todos as you progress

Read the full file on GitHub · 102 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. 8d ago First seen · 102 lines · 11 tokens per session scan A fbc46307ab8f

Subscribe to this mod's changes

team is a command published in the GitHub repository MonumentalSystems/Atlas-Agent-Teams (21 stars, last pushed 27d ago), licensed MIT. It adds 11 tokens to every session and 609 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 2026-08-30.