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.
npx skills add shwilliamson/automatasaurus --skill team-coordinationgit clone --depth 1 https://github.com/shwilliamson/automatasaurusWrote 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.
[](https://agentmods.dev/skills/shwilliamson/automatasaurus/team-coordination)<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>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.
| Model | Per session | Once 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 |
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.
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
teamPreferForReviewsorteamPreferForImplementationistruein 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:
- Create the team with clear goals and teammate roles
- Set up shared tasks describing what needs to be done
- Let teammates claim and complete tasks independently
- Monitor progress via the shared task list
- 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.
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.
- 8d ago First seen · 265 lines · 32 tokens per session scan A bd0f49abfb3d
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.