agent-coordination

agent-coordination is a skill for Claude Code, Codex from shwilliamson/automatasaurus. It costs 23 tokens per session (3,776 once invoked), scanned A, original, MIT.

A guide for assigning work to specialist coding agents and coordinating their results. It describes separate subagents and shared agent teams, which let multiple roles contribute to a task.

In plain words
What is it for?
Use it when delegating implementation, architecture, design, testing, or other specialist tasks to coding agents.
Why use it?
It helps choose an appropriate way to divide work and keeps communication and fallback options clear when several coding or review tasks are involved.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents.

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.

agentmods
npx agentmods add skills/shwilliamson/automatasaurus/agent-coordination
Any agent
npx skills add shwilliamson/automatasaurus --skill agent-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 agent-coordination

README.md
[![agentmods](https://agentmods.dev/badge/skills/shwilliamson/automatasaurus/agent-coordination.svg)](https://agentmods.dev/skills/shwilliamson/automatasaurus/agent-coordination)
Your own site
<a href="https://agentmods.dev/skills/shwilliamson/automatasaurus/agent-coordination"><img src="https://agentmods.dev/badge/skills/shwilliamson/automatasaurus/agent-coordination.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,776 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 $0.00023 $0.03776
Opus 5 $0.00012 $0.01888
Sonnet 5 $0.00005 $0.00755
Haiku 4.5 $0.00002 $0.00378

Measured 5d ago against content hash f15bd3d81aa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent-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 5d 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/agent-coordination/SKILL.md · 593 lines

How it starts

The opening of the file, as written. The whole thing — 593 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Coordination Skill

This skill provides patterns for invoking the Automatasaurus agents and managing bidirectional context flow.

Coordination Modes

Automatasaurus supports two modes for coordinating agent work:

Mode Mechanism Communication Best For
Subagents (default) Task tool Report to orchestrator only Single-role tasks, linear workflows
Agent Teams (experimental) Team creation Peer-to-peer messaging + shared tasks Multi-role reviews, real-time collaboration

Decision criteria:

  • Use subagents when tasks are independent and don't benefit from real-time coordination
  • Use teams when agents should share findings and coordinate in real-time (e.g., review cycles)
  • Check teamPreferForReviews and teamPreferForImplementation in settings for project defaults
  • Always have a fallback to subagents — teams are experimental

For detailed team patterns, load the team-coordination skill.

Available Agents

Agent Purpose When to Use
developer Implements issues, creates PRs When code needs to be written
architect Technical reviews, analysis For PR reviews, discovery reviews, stuck issues
designer UI/UX reviews, design specs For PR reviews, discovery reviews, design specs
researcher Deep research, technology evaluation When any agent needs thorough research on a topic
tester Testing, verification For PR verification, running tests

Bidirectional Context Flow

Sub-agents start with fresh context (no conversation history). Use briefing and report files to communicate context and capture results.

Orchestration Folder Structure

orchestration/
├── discovery/
│   └── {date}-{feature-slug}/
│       ├── BRIEFING-architect-review.md
│       ├── REPORT-architect-review.md
│       └── ...
├── planning/
│   └── {date}-{plan-name}/
│       └── ...
└── issues/
    └── {issue-number}-{slug}/
        ├── BRIEFING-design-specs.md
        ├── REPORT-design-specs.md
        ├── BRIEFING-implement.md
        ├── REPORT-implement.md
        ├── BRIEFING-architect-review.md
        ├── REPORT-architect-review.md
        ├── BRIEFING-designer-review.md
        ├── REPORT-designer-review.md
        ├── BRIEFING-test.md
        └── REPORT-test.md

Read the full file on GitHub · 593 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. 5d ago First seen · 593 lines · 23 tokens per session scan A f15bd3d81aa0

Subscribe to this mod's changes

agent-coordination is a skill published in the GitHub repository shwilliamson/automatasaurus (5 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 3,776 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens