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.
curl -O https://raw.githubusercontent.com/sawadari/requirements-mcp-server/main/.claude/commands/miyabi-agent.mdgit clone --depth 1 https://github.com/sawadari/requirements-mcp-serverWrote 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/commands/sawadari/requirements-mcp-server/miyabi-agent)<a href="https://agentmods.dev/commands/sawadari/requirements-mcp-server/miyabi-agent"><img src="https://agentmods.dev/badge/commands/sawadari/requirements-mcp-server/miyabi-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/sawadari/requirements-mcp-server/miyabi-agent"><img src="https://agentmods.dev/badge/commands/sawadari/requirements-mcp-server/miyabi-agent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00012 | $0.00868 |
| Opus 5 | $0.00006 | $0.00434 |
| Sonnet 5 | $0.00002 | $0.00174 |
| Haiku 4.5 | $0.00001 | $0.00087 |
Grade A, and why
miyabi-agent 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 9d 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.
What it actually says
Miyabi Agent実行
GitHub IssueをMiyabi Autonomous Agentで自動処理します。
利用可能なMCPツール
Claude CodeからMiyabi機能を直接呼び出せます:
miyabi__agent_run
Autonomous Agentを実行してIssueを自動処理
パラメータ:
issueNumber: 処理するIssue番号issueNumbers: 複数Issue(並列処理)concurrency: 並行実行数(デフォルト: 2)dryRun: ドライラン(デフォルト: false)
使用例:
単一Issue処理:
miyabi__agent_run({ issueNumber: 123 })
複数Issue並列処理:
miyabi__agent_run({ issueNumbers: [123, 124, 125], concurrency: 3 })
Dry run:
miyabi__agent_run({ issueNumber: 123, dryRun: true })
miyabi__auto
Water Spider Agent(全自動モード)起動
パラメータ:
maxIssues: 最大処理Issue数(デフォルト: 5)interval: ポーリング間隔秒(デフォルト: 60)
使用例:
全自動モード起動:
miyabi__auto({ maxIssues: 10, interval: 30 })
実行フロー
Issue作成/検出
↓
CoordinatorAgent(タスク分解・DAG構築)
↓ 並行実行
├─ IssueAgent(分析・Label付与)
├─ CodeGenAgent(Claude Sonnet 4でコード生成)
├─ ReviewAgent(品質チェック≥80点)
└─ TestAgent(テスト実行)
↓
PRAgent(Draft PR作成)
↓
人間レビュー待ち
コマンドライン実行
MCPツールの代わりにコマンドラインでも実行可能:
# 単一Issue処理
npx miyabi agent run --issue 123
# 複数Issue並行処理
npx miyabi agent run --issues 123,124,125 --concurrency 3
# 全自動モード
npx miyabi auto --max-issues 10
# Dry run
npx miyabi agent run --issue 123 --dry-run
環境変数
.env ファイルに以下を設定:
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 |
💡 ヒント: MCPツールを使うと、Claude Codeが自動的にパラメータを推論して実行します。
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.
- 9d ago First seen · 121 lines · 12 tokens per session scan A c8f24405c034
miyabi-agent is a command published in the GitHub repository sawadari/requirements-mcp-server (2 stars, last pushed 10mo ago), licensed MIT. It adds 12 tokens to every session and 868 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.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.