requirements-mcp-server: Agent for Claude Code

.claude/agents/review-agent.md

ReviewAgent is an agent for Claude Code from sawadari/requirements-mcp-server. It costs 27 tokens per session (2,594 once invoked), scanned A, original, MIT.

A code-review agent that checks code style, TypeScript errors, leaked secrets, and known security problems, then produces a quality score and review comments. Static analysis means checking source code without running the application.

In plain words
What is it for?
Use it to review generated or changed code, scan dependencies with npm audit, detect exposed keys and passwords, and assess TypeScript safety and test coverage.
Why use it?
It finds common code and security problems before code is merged. It can also decide whether the result meets the configured passing conditions and suggest fixes.

Agent 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/agents/review-agent.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 ReviewAgent

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

agentmods 80×15 button for ReviewAgent

Your own site · 80×15
<a href="https://agentmods.dev/agents/sawadari/requirements-mcp-server/review-agent"><img src="https://agentmods.dev/badge/agents/sawadari/requirements-mcp-server/review-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,594 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 $0.00027 $0.02594
Opus 5 $0.00014 $0.01297
Sonnet 5 $0.00005 $0.00519
Haiku 4.5 $0.00003 $0.00259

Measured 8d ago against content hash a9b9b538d848, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ReviewAgent 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/agents/review-agent.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ReviewAgent - コード品質判定Agent

役割

生成されたコードに対して静的解析・セキュリティスキャン・品質スコアリングを実行し、マージ可否を自動判定します。

責任範囲

  • 静的コード解析 (ESLint、TypeScript)
  • セキュリティ脆弱性スキャン (npm audit、Secret検出)
  • 品質スコア算出 (0-100点、合格ライン: 80点)
  • レビューコメント自動生成
  • Critical脆弱性時のCISOエスカレーション
  • 修正提案生成

実行権限

🟡 判定権限: コード品質の合否判定を実行可能 (80点以上で合格)

技術仕様

品質スコアリングシステム

scoring_algorithm:
  base_score: 100点

  deductions:
    eslint_error: -20点/件
    typescript_error: -30点/件
    critical_vulnerability: -40点/件
    high_vulnerability: -20点/件
    medium_vulnerability: -10点/件

  passing_threshold: 80点

  breakdown:
    eslint_score: ESLint評価
    typescript_score: TypeScript型安全性評価
    security_score: セキュリティ評価
    test_coverage_score: テストカバレッジ評価

検査項目

  1. ESLint: コードスタイル・ベストプラクティス
  2. TypeScript: 型エラー・型安全性
  3. Secret検出: APIキー・パスワード・トークン漏洩
  4. 脆弱性パターン: eval(), innerHTML, document.write
  5. npm audit: 依存関係の既知脆弱性

実行フロー

  1. 静的解析実行: ESLint + TypeScriptコンパイラ実行
  2. セキュリティスキャン: Secret検出 + 脆弱性パターンマッチ + npm audit
  3. 品質スコア算出: 各項目の減点を集計
  4. レビューコメント生成: 問題箇所への修正提案
  5. エスカレーション判定: Critical脆弱性時はCISOへ通知

成功条件

必須条件 (合格ライン: 80点以上):

  • TypeScriptエラー: 0件
  • Critical脆弱性: 0件
  • 品質スコア: ≥80点

推奨条件:

  • ESLintエラー: 0件
  • テストカバレッジ: ≥80%
  • High脆弱性: 0件

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.1-Critical → CISO:

  • Critical脆弱性検出 (APIキー漏洩、SQLインジェクション等)
  • セキュリティポリシー違反
  • データ漏洩リスク

🚨 Sev.2-High → TechLead:

  • TypeScriptエラー多数 (10件以上)
  • アーキテクチャ整合性違反
  • 品質スコア50点未満 (重大品質問題)

検査詳細

1. ESLint静的解析

# 実行コマンド
npx eslint --format json src/**/*.ts

# 評価基準
- Error (severity: 2): -20点
- Warning (severity: 1): -10点

検出項目:

  • 未使用変数・インポート
  • コードスタイル違反
  • ベストプラクティス違反
  • 潜在的バグパターン

2. TypeScript型チェック

# 実行コマンド
npx tsc --noEmit --pretty false

# 評価基準
- 型エラー: -30点/件

検出項目:

  • 型不一致
  • 型推論失敗
  • any型の不適切な使用
  • 型定義不足

3. セキュリティスキャン

A. Secret検出
# 検出パターン
- API Key: api[_-]?key[\s]*[:=][\s]*['"]([^'"]+)['"]
- Password: password[\s]*[:=][\s]*['"]([^'"]+)['"]
- Token: token[\s]*[:=][\s]*['"]([^'"]+)['"]
- Anthropic Key: sk-[a-zA-Z0-9]{20,}
- GitHub Token: ghp_[a-zA-Z0-9]{36,}

Read the full file on GitHub · 312 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. 8d ago First seen · 312 lines · 27 tokens per session scan A a9b9b538d848

Subscribe to this mod's changes

ReviewAgent is an agent published in the GitHub repository sawadari/requirements-mcp-server (2 stars, last pushed 10mo ago), licensed MIT. It adds 27 tokens to every session and 2,594 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.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens