requirements-mcp-server: Command for Claude Code

.claude/commands/miyabi-auto.md

miyabi-auto is a command for Claude Code from sawadari/requirements-mcp-server. It costs 12 tokens per session (1,950 once invoked), scanned A, original, MIT.

A command that watches GitHub Issues and automatically sends them through analysis, code generation, review, and draft pull-request creation.

In plain words
What is it for?
Use it to process several GitHub Issues automatically, prioritising urgent, security-related, unblocked, small, or older issues.
Why use it?
It reduces the manual work of finding issues, deciding what to do first, and moving each task through development. Human review is still needed for the resulting draft pull requests.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is sawadari/requirements-mcp-server's own configuration. It tells Claude Code how to work on requirements-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything requirements-mcp-server configures →

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/miyabi-auto.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.

agentmods badge for miyabi-auto

README.md
[![agentmods](https://agentmods.dev/badge/commands/sawadari/requirements-mcp-server/miyabi-auto/github.svg)](https://agentmods.dev/commands/sawadari/requirements-mcp-server/miyabi-auto)
Your own site
<a href="https://agentmods.dev/commands/sawadari/requirements-mcp-server/miyabi-auto"><img src="https://agentmods.dev/badge/commands/sawadari/requirements-mcp-server/miyabi-auto/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.

agentmods 80×15 button for miyabi-auto

Your own site · 80×15
<a href="https://agentmods.dev/commands/sawadari/requirements-mcp-server/miyabi-auto"><img src="https://agentmods.dev/badge/commands/sawadari/requirements-mcp-server/miyabi-auto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,950 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.01950
Opus 5 $0.00006 $0.00975
Sonnet 5 $0.00002 $0.00390
Haiku 4.5 $0.00001 $0.00195

Measured 10d ago against content hash e3b0a58d4472, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

miyabi-auto 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 10d 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/miyabi-auto.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Miyabi Water Spider全自動モード

Water Spider Agent(水すまし)を起動して、GitHub Issueを自動的に検出・処理します。

MCPツール

miyabi__auto

Water Spider全自動モードを起動

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(デフォルト設定):
miyabi__auto({})

最大10 Issue、30秒間隔:
miyabi__auto({ maxIssues: 10, interval: 30 })

動作フロー

Water Spider Agent起動
    ↓
GitHub Issueポーリング(60秒ごと)
    ↓
未処理Issueを検出
    ↓
優先順位付け(緊急度・規模・種別)
    ↓
CoordinatorAgent起動
    ↓
├─ IssueAgent(分析・Label付与)
├─ CodeGenAgent(コード生成)
├─ ReviewAgent(品質チェック)
└─ PRAgent(Draft PR作成)
    ↓
次のIssueへ(maxIssues到達まで繰り返し)

優先順位付けロジック

Water Spiderは以下の順序でIssueを処理します:

  1. 緊急度が高い: 緊急度-高, 緊急度-即時 ラベル付き
  2. セキュリティ関連: security, vulnerability ラベル付き
  3. ブロッカー: status:blocked 以外で、依存関係が解決済み
  4. 規模が小さい: 規模-小 ラベル付き(クイックウィン)
  5. 作成日時が古い: FIFOで公平に処理

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:

# デフォルト設定で起動
npx miyabi auto

# 最大Issue数と間隔を指定
npx miyabi auto --max-issues 10 --interval 30

# 1回だけ実行(ポーリングなし)
npx miyabi auto --max-issues 5 --interval 0

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

停止方法

MCPツール経由

Water Spiderはバックグラウンドで実行されないため、Claude Codeセッション終了時に自動停止します。

CLI経由

# Ctrl+C で停止
^C

プログラム的停止

# maxIssues到達で自動停止
npx miyabi auto --max-issues 3

# interval=0 で1回のみ実行
npx miyabi auto --interval 0

成功条件

Water Spiderが正常に動作するための条件:

環境:

  • GITHUB_TOKEN が設定済み
  • ANTHROPIC_API_KEY が設定済み(CodeGenAgent用)
  • REPOSITORY が正しい形式(owner/repo)

権限:

  • GitHubトークンに repo, workflow 権限
  • リポジトリへの書き込み権限

Issue:

  • 未処理Issueが存在する
  • Issueがブロック状態でない(status:blocked ラベルなし)

処理結果の確認

GitHub上で確認

# 処理されたIssueを確認
gh issue list --label "status:in-progress"

# 作成されたPRを確認
gh pr list --label "automated"

# Projectsボードで進捗確認
gh project list

Read the full file on GitHub · 262 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. 10d ago First seen · 262 lines · 12 tokens per session scan A e3b0a58d4472

Subscribe to this mod's changes

miyabi-auto 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 1,950 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.