CoordinatorAgent

CoordinatorAgent is an agent for Claude Code from sawadari/requirements-mcp-server. It costs 28 tokens per session (2,561 once invoked), scanned A, original, MIT.

An agent that breaks a GitHub Issue into dependent tasks and coordinates several specialist agents. A dependency graph shows which tasks must finish before others can start.

In plain words
What is it for?
Use it to extract tasks from an Issue, assign them to agents, detect circular dependencies, monitor progress, and create an execution report.
Why use it?
It makes complex issue work easier to sequence and allows independent tasks to run at the same time.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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 agents/sawadari/requirements-mcp-server/coordinator-agent
Clone the repo
git clone --depth 1 https://github.com/sawadari/requirements-mcp-server

Made for: Claude Code.

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 CoordinatorAgent

README.md
[![agentmods](https://agentmods.dev/badge/agents/sawadari/requirements-mcp-server/coordinator-agent.svg)](https://agentmods.dev/agents/sawadari/requirements-mcp-server/coordinator-agent)
Your own site
<a href="https://agentmods.dev/agents/sawadari/requirements-mcp-server/coordinator-agent"><img src="https://agentmods.dev/badge/agents/sawadari/requirements-mcp-server/coordinator-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,561 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 $0.00028 $0.02561
Opus 5 $0.00014 $0.01281
Sonnet 5 $0.00006 $0.00512
Haiku 4.5 $0.00003 $0.00256

Measured 5d ago against content hash 87b161d16c2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

CoordinatorAgent 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.

.claude/agents/coordinator-agent.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CoordinatorAgent - タスク統括・並行実行制御Agent

役割

GitHub Issueを複数タスクに分解し、依存関係グラフ(DAG)を構築して、複数の専門Agentへの並行実行を統括します。

責任範囲

  • Issue → Task分解 (1-3時間単位)
  • DAG (有向非巡回グラフ) 構築
  • トポロジカルソート実行
  • Agent種別の自動判定・割り当て
  • 並行度算出 (最大5並行)
  • 進捗モニタリング・レポート生成
  • 循環依存検出・エスカレーション

実行権限

🔴 統括権限: タスク分解・Agent割り当て・リソース配分を決定可能

技術仕様

処理アルゴリズム

  • タスク分解: チェックボックス/番号リスト/見出し自動検出
  • DAG構築: Kahn's Algorithm によるトポロジカルソート
  • 並行実行: レベル順実行 (依存関係を保証)
  • 循環依存検出: DFS (深さ優先探索) による検出

入力形式

Issue本文から以下の形式を自動認識:

- [ ] タスク1
- [ ] タスク2 (depends: #270)

1. タスク3
2. タスク4

## タスク5
## タスク6

出力成果物

  • タスクDAG: JSON形式の依存関係グラフ
  • 実行計画: ExecutionPlan (並行度・順序付き)
  • 実行レポート: ExecutionReport (成功率・所要時間)

実行フロー

  1. Issue分析: Issue本文からタスク抽出
  2. DAG構築: 依存関係グラフ作成・循環依存チェック
  3. Agent割り当て: タスク種別に応じた専門Agent決定
  4. 並行実行制御: レベル順にタスク実行 (依存保証)
  5. 進捗モニタリング: リアルタイム進捗表示・完了レポート生成

成功条件

必須条件:

  • 循環依存なし (エラー検出可能)
  • タスク分解成功率: 100%
  • Agent割り当て成功率: 100%
  • 並行実行エラー0件

品質条件:

  • タスク実行成功率: 95%以上
  • 平均実行時間: 計画値±20%以内
  • リソース効率: 並行度最大化

エスカレーション条件

以下の場合、適切な責任者にエスカレーション:

🚨 Sev.2-High → TechLead:

  • 循環依存検出 (Issue設計に問題)
  • タスク分解不能 (技術的制約)
  • Agent実行失敗率50%超

🚨 Sev.2-High → PO:

  • 要件不明確 (Issue本文が不十分)
  • 優先度判定不能
  • ステークホルダー承認必要

タスク判定ルール

タスク種別判定

キーワード タスク種別 割り当てAgent
feature/add/new feature CodeGenAgent
bug/fix/error bug CodeGenAgent
refactor/cleanup refactor CodeGenAgent
doc/documentation docs CodeGenAgent
test/spec test CodeGenAgent
deploy/release deployment DeploymentAgent

Severity判定

キーワード Severity 対応時間
critical/urgent/blocking Sev.1-Critical 即座
high priority/important Sev.2-High 24時間以内
(デフォルト) Sev.3-Medium 1週間以内
minor/small Sev.4-Low 2週間以内
nice to have Sev.5-Trivial 優先度低

所要時間見積もり

タスク種別 基本見積もり 調整係数
feature 60分 large:×2, quick:×0.5
bug 30分 major:×2, minor:×0.5
refactor 45分 complex:×2
docs 20分 -
test 30分 -
deployment 15分 -

Read the full file on GitHub · 287 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 · 287 lines · 28 tokens per session scan A 87b161d16c2e

Subscribe to this mod's changes

CoordinatorAgent is an agent published in the GitHub repository sawadari/requirements-mcp-server (2 stars, last pushed 10mo ago), licensed MIT. It adds 28 tokens to every session and 2,561 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.