A command that processes one or more GitHub Issues through task breakdown, code generation, quality checks, and draft pull-request creation. A draft pull request is a proposed code change that is waiting for human review.

Use it to handle individual or multiple Issues, run tasks concurrently, check the planned work with dry-run mode, and create draft pull requests after review checks.

It groups the routine steps of turning an Issue into a proposed change, while retaining a human checkpoint before merging. Dry-run mode lets you inspect the process without making changes.

How sawadari/requirements-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sawadari/requirements-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sawadari/requirements-mcp-server/main/.claude/commands/agent-run.md

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/sawadari/requirements-mcp-server/agent-run.svg)](https://agentmods.dev/commands/sawadari/requirements-mcp-server/agent-run)

Your own site

<a href="https://agentmods.dev/commands/sawadari/requirements-mcp-server/agent-run"><img src="https://agentmods.dev/badge/commands/sawadari/requirements-mcp-server/agent-run.svg" alt="Measured on agentmods" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,319 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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.01319
Opus 5	$0.00008	$0.00660
Sonnet 5	$0.00003	$0.00264
Haiku 4.5	$0.00002	$0.00132

Measured 8d ago against content hash 9a28780ac6ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-run 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.

.claude/commands/agent-run.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Agent実行

GitHub IssueをAutonomous Agentシステムで自動処理します。

実行フロー

Issue作成/検出
    ↓
CoordinatorAgent（タスク分解・DAG構築）
    ↓ 並行実行
├─ IssueAgent（Issue分析・Label付与）
├─ CodeGenAgent（コード生成）
├─ ReviewAgent（品質チェック≥80点）
└─ PRAgent（PR作成）
    ↓
Draft PR作成
    ↓
人間レビュー待ち

コマンド

単一Issue処理

npm run agents:parallel:exec -- --issue 123

複数Issue並行処理

npm run agents:parallel:exec -- --issues 123,124,125 --concurrency 3

Dry run（確認のみ、変更なし）

npm run agents:parallel:exec -- --issue 123 --dry-run

ヘルプ表示

npm run agents:parallel:exec -- --help

オプション

オプション	説明	デフォルト
`--issue <number>`	単一Issue番号	-
`--issues <n1,n2,...>`	複数Issue番号（カンマ区切り）	-
`--concurrency <number>`	並行実行数	2
`--dry-run`	実行のみ（変更なし）	false
`--log-level <level>`	ログレベル	info

環境変数

必須環境変数（.envファイル）:

GITHUB_TOKEN=ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
ANTHROPIC_API_KEY=sk-ant-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
REPOSITORY=owner/repo
DEVICE_IDENTIFIER=MacBook Pro 16-inch

成功条件

✅ 必須:

Issue分析完了
コード生成成功
品質スコア ≥80点
Draft PR作成

✅ 品質:

TypeScriptエラー 0件
ESLintエラー 0件
セキュリティスキャン合格
テストカバレッジ ≥80%

エスカレーション

以下の場合、自動エスカレーション:

条件	エスカレーション先	重要度
アーキテクチャ問題	TechLead	Sev.2-High
セキュリティ脆弱性	CISO	Sev.1-Critical
ビジネス優先度	PO	Sev.3-Medium
循環依存検出	TechLead	Sev.2-High

実行例

例1: 単一Issue処理

$ npm run agents:parallel:exec -- --issue 270

🤖 Autonomous Operations - Parallel Executor

✅ Configuration loaded
   Device: MacBook Pro 16-inch
   Repository: ShunsukeHayashi/Autonomous-Operations
   Concurrency: 2

✅ Fetched Issue #270: Add user authentication

================================================================================
🚀 Executing Issue #270: Add user authentication
================================================================================

[CoordinatorAgent] 🔍 Decomposing Issue #270
[CoordinatorAgent]    Found 4 tasks
[CoordinatorAgent] 🔗 Building task dependency graph (DAG)
[CoordinatorAgent]    Graph: 4 nodes, 0 edges, 1 levels
[CoordinatorAgent] ✅ No circular dependencies found

[CodeGenAgent] 🧠 Generating code with Claude AI
[CodeGenAgent]    Generated 3 files

[ReviewAgent] 📊 Calculating quality score
[ReviewAgent]    Score: 85/100 ✅

[PRAgent] 🚀 Creating Pull Request
[PRAgent] ✅ PR created: #271

✅ Issue #270 completed successfully
   Duration: 45,234ms

Read the full file on GitHub · 207 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.

8d ago First seen · 207 lines · 15 tokens per session scan A 9a28780ac6ea

Subscribe to this mod's changes

agent-run is a command published in the GitHub repository sawadari/requirements-mcp-server (2 stars, last pushed 10mo ago), licensed MIT. It adds 15 tokens to every session and 1,319 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.

Git and workflow Planning

commit

A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.

echoVic/blade-code · 8 tokens

merge-conflict-analysis

You are analyzing merge conflicts for PR #${{ pr-number }}.

rjmurillo/ai-agents · 0 tokens

release-notes

Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.

OpenHands/extensions · 44 tokens

doctor

Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…

doncheli/don-cheli-sdd · 76 tokens

repo-audit

Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.

tractorjuice/arc-kit · 29 tokens

handoff

Export a Waybill Bundle by default, or import one when requested.

wardmos/waybill · 13 tokens

requirements-mcp-server: Command for Claude Code