team-coordination

team-coordination is a skill for Claude Code, Codex from shwilliamson/automatasaurus. It costs 32 tokens per session (1,942 once invoked), scanned A, original, MIT.

Patterns for coordinating several Claude Code sessions as an agent team, where independent agents share tasks and communicate directly.

In plain words
What is it for?
Organizing multi-agent reviews or implementation work, sharing task status, exchanging messages, and keeping an audit trail of the work.
Why use it?
They clarify when team coordination is useful and how it differs from assigning isolated tasks to separate agents.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code.

Good fit Organizing multi-agent reviews or implementation work, sharing task status, exchanging messages, and keeping an audit trail of the work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shwilliamson/automatasaurus/team-coordination
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.

Any agent
npx skills add shwilliamson/automatasaurus --skill team-coordination
Clone the repo
git clone --depth 1 https://github.com/shwilliamson/automatasaurus

Made for: Claude Code, Codex.

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-coordination

README.md
[![agentmods](https://agentmods.dev/badge/skills/shwilliamson/automatasaurus/team-coordination.svg)](https://agentmods.dev/skills/shwilliamson/automatasaurus/team-coordination)
Your own site
<a href="https://agentmods.dev/skills/shwilliamson/automatasaurus/team-coordination"><img src="https://agentmods.dev/badge/skills/shwilliamson/automatasaurus/team-coordination.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,942 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 $0.00032 $0.01942
Opus 5 $0.00016 $0.00971
Sonnet 5 $0.00006 $0.00388
Haiku 4.5 $0.00003 $0.00194

Measured 8d ago against content hash bd0f49abfb3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

team-coordination 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.

template/skills/team-coordination/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Coordination Skill

This skill provides patterns for using Claude Code's experimental agent teams feature. Teams enable multiple independent Claude Code sessions that coordinate via shared task lists and peer-to-peer messaging.

When to Load This Skill

Load this skill when:

  • The orchestrator decides to use teams for reviews or implementation
  • teamPreferForReviews or teamPreferForImplementation is true in settings
  • You're about to spawn multiple agents that would benefit from real-time coordination

Teams vs Subagents

Aspect Subagents (Task tool) Agent Teams
Communication Report to orchestrator only Message each other directly
Context Fresh context per spawn Fresh context, but shared task list
Coordination Sequential briefing/report chain Real-time peer collaboration
Best for Single-role tasks, linear workflows Multi-role tasks, cross-pollination
Audit trail BRIEFING/REPORT files BRIEFING/REPORT files + shared task list
Cost One session per agent Multiple concurrent sessions
Reliability Stable Experimental — may need fallback

Team Creation

Teams are created using natural language prompts. The orchestrator creates a team by describing the goal and teammates.

Key principle: The orchestrator acts as team lead in delegate mode — it coordinates but does not implement.

Delegate Mode

When leading a team, the orchestrator should:

  1. Create the team with clear goals and teammate roles
  2. Set up shared tasks describing what needs to be done
  3. Let teammates claim and complete tasks independently
  4. Monitor progress via the shared task list
  5. Synthesize results when the team completes

Do NOT implement work yourself when leading a team. Your role is coordination.


Team Patterns

Review Team

When to use: PR reviews where cross-pollination of findings adds value. The architect might flag a concern that the tester should verify, or the designer might notice an accessibility issue that affects the architect's assessment.

Read the full file on GitHub · 265 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 · 265 lines · 32 tokens per session scan A bd0f49abfb3d

Subscribe to this mod's changes

team-coordination is a skill published in the GitHub repository shwilliamson/automatasaurus (5 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 1,942 once invoked, about $0.0002 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.