agent-team-guide

agent-team-guide is a skill for Claude Code from sean-sunagaku/claude-code-plugin. It costs 253 tokens per session (2,479 once invoked), scanned A, original, MIT.

A guide for designing and building teams of coding sub-agents. It covers role definitions, communication, task dependencies, logging, tool connections, and files that preserve knowledge between sessions.

In plain words
What is it for?
Use it to create or audit agent-team skills, define three to six distinct roles, design multi-phase workflows, set up agent instructions, and add templates or initialization scripts.
Why use it?
It gives a repeatable structure for splitting work among several agents without overlapping responsibilities or losing shared context. It also supports reviewing the quality of an existing team skill.

Skill for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions subagents.

Part of the agent-team-guide plugin — 1 skill shipped together

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/sean-sunagaku/claude-code-plugin/agent-team-guide
Any agent
npx skills add sean-sunagaku/claude-code-plugin --skill agent-team-guide
Clone the repo
git clone --depth 1 https://github.com/sean-sunagaku/claude-code-plugin

Made for: Claude Code.

Or install agent-team-guide, the plugin that ships this one along with the rest of its 1 skill.

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-team-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/sean-sunagaku/claude-code-plugin/agent-team-guide.svg)](https://agentmods.dev/skills/sean-sunagaku/claude-code-plugin/agent-team-guide)
Your own site
<a href="https://agentmods.dev/skills/sean-sunagaku/claude-code-plugin/agent-team-guide"><img src="https://agentmods.dev/badge/skills/sean-sunagaku/claude-code-plugin/agent-team-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 253 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,479 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 $0.00253 $0.02479
Opus 5 $0.00127 $0.01239
Sonnet 5 $0.00051 $0.00496
Haiku 4.5 $0.00025 $0.00248

Measured 6d ago against content hash 263b50b22598, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-team-guide 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.

agent-toolkit/agent-team-guide/skills/agent-team-guide/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Team Guide

7つの実績あるチームスキルから抽出した Agent Teams 設計パターン集。 新規チームスキルの作成と、既存スキルの品質監査の両方に使える。

このスキルの使い方

新規作成: SKILL.md テンプレート → エージェント定義 → タスク設計 → テスト の順で構築 品質監査: references/quality-checklist.md を既存スキルに適用し、改善点を特定

チームスキルのディレクトリ構成

my-team-skill/
├── SKILL.md                    <- リーダーの手順書(ワークフロー全体)
├── agents/                     <- サブエージェント定義
│   ├── role-a.md
│   ├── role-b.md
│   └── context-manager.md      <- ファイル I/O 専任を推奨
├── references/                 <- テンプレート・ドメイン知識
│   └── report-template.md
└── scripts/                    <- 初期化・ユーティリティ
    └── init.sh

設計の5原則

  1. エージェント数は 3〜6 体: 少なすぎると並列の意味なし、多すぎると通信爆発
  2. MECE な役割分担: 各エージェントの責務が重複しない
  3. 3-Phase ワークフロー: 全エージェントが init → active → finalize の構造
  4. 実質的通信のみ: ACK だけの返信は不要。相手の次アクションに繋がる内容がある時のみ返信
  5. 待ちすぎない: 全員のフィードバックを待たない。2人以上から反応があれば次へ進む
  6. コンテキストファイルで永続化: セッション跨ぎの知識蓄積

SKILL.md テンプレート

## Step 1: ヒアリング
以下を確認する(不明ならユーザーに質問):
- **項目A**: {具体的に何を聞くか}
- **項目B**: ...

## Step 2: チーム作成とエージェント起動

TeamCreate で `{skill-name}` チームを作成。
以下 N エージェントを **1つのメッセージで並列に** Task ツールで起動する。

| name | 役割 | 主な手段 |
|------|------|---------|
| `role-a` | ... | 分析 |
| `role-b` | ... | WebSearch |

### タスク作成
TaskCreate で N+1 個のタスクを作成:
1. context-manager: 初期化(依存なし)
2. role-a: ...(`addBlockedBy: ["1"]`)
3. role-b: ...(依存なし or `addBlockedBy: ["1"]`)
4. ...(`addBlockedBy: ["2","3"]`)
5. 統合レポート(`addBlockedBy: ["1","2","3","4"]`)

### 起動設定(全エージェント共通)
subagent_type: "{skill-name}:{role-name}"
team_name: "{skill-name}"
mode: "bypassPermissions"
run_in_background: true

プロンプトに含める情報:
- ユーザーからヒアリングした全情報
- コンテキストファイルパス
- 既存の context.md 内容(あれば)

## Step 3: フィードバックループ

### フィードバックプロトコル
1. 自分の作業完了後、即座に関連エージェントへ共有
2. **実質的な内容のある返信のみ送る** - 「了解しました」「ありがとうございます」だけのACK返信は不要。フィードバック・質問・修正報告など、相手の次アクションに繋がる内容がある場合のみ返信する
3. 重大問題は即座に全員へ緊急通知
4. フィードバックを受けたら修正し、変更内容を共有
5. **待ちすぎない** - フィードバックを全員から集める必要はない。2人以上から反応があれば次のフェーズに進む

### Round 1: {概要}
{エージェント間の通信フロー}

### Round 2: {概要}
...

### Round 3: {概要}
...

### 緊急通知パターン
- **role-a**: {どんな問題を検知したら} → {誰にどうアクションを求めるか}
- **role-b**: ...

## Step 4: 最終レポート出力
テンプレート: [references/report-template.md](references/report-template.md)

## Step 5: クリーンアップ
1. 全エージェントに shutdown_request を送信
2. 全員シャットダウン後に TeamDelete でチーム削除

Read the full file on GitHub · 174 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 174 lines · 253 tokens per session scan A 263b50b22598

Subscribe to this mod's changes

agent-team-guide is a skill published in the GitHub repository sean-sunagaku/claude-code-plugin (36 stars, last pushed 1mo ago), licensed MIT. It adds 253 tokens to every session and 2,479 once invoked, about $0.0013 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.

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

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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