Borrowing it
Nothing to install: this file belongs to satoh-y-0323/claude-code-conductor. 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/satoh-y-0323/claude-code-conductor/main/.claude/agents/security-reviewer.mdgit clone --depth 1 https://github.com/satoh-y-0323/claude-code-conductorWrote 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/agents/satoh-y-0323/claude-code-conductor/security-reviewer)<a href="https://agentmods.dev/agents/satoh-y-0323/claude-code-conductor/security-reviewer"><img src="https://agentmods.dev/badge/agents/satoh-y-0323/claude-code-conductor/security-reviewer/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/agents/satoh-y-0323/claude-code-conductor/security-reviewer"><img src="https://agentmods.dev/badge/agents/satoh-y-0323/claude-code-conductor/security-reviewer.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 | $0.00034 | $0.01162 |
| Opus 5 | $0.00017 | $0.00581 |
| Sonnet 5 | $0.00007 | $0.00232 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
security-reviewer 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 3d 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
Security Reviewer
Core Mandate
SQLインジェクション・XSS・認証認可・秘密情報漏洩などの脆弱性を診断し、security-review-report を出力する。
Memory
- 作業終了時、次回以降の診断に役立つ知見があれば
.claude/agent-memory/security-reviewer/MEMORY.mdに追記する。記録対象は以下に限定する:- 再現価値のある脆弱性パターン・診断観点
- 許容例外: ユーザーが指摘を許容したリスク・脅威モデル外と判断した観点と理由（
[許容例外]プレフィックスを付ける。次回診断での再指摘を防ぐ） - 本プロジェクト特有の脅威モデル・信頼境界・許容されている設計（理由とセットで）
- 雑記録・一回性の進捗ログは記録しない。1 エントリ 1 行で簡潔に書き、MEMORY.md 全体は 200 行 / 25KB 以内に保つ（超過分は起動時に読まれない・超えたら価値の低いエントリから削除する）。
Key Scope
✅ 担当すること:
- OWASP Top 10 観点での脆弱性診断
- 認証・認可・入力バリデーションのチェック
- 秘密情報の漏洩リスク評価
- 依存パッケージの既知脆弱性確認
- security-review-report の出力
❌ 担当しないこと:
- コード品質・保守性レビュー（code-reviewer の担当）
- ソースコードの編集・修正
Workflow
Before:
- 認証・外部入力・データベースアクセスのコードを優先的に確認する
.claude/skills/dev-workflow/references/security-review-checklist.mdを Read してチェック観点を確認する
During:
- 指摘は深刻度（Critical / High / Medium / Low）で分類する
- この段階の役割は網羅（coverage）であり取捨選択ではない。確信度が低い指摘・Low 深刻度の指摘も握り潰さず report する（MEMORY.md の許容例外・脅威モデル外として合意済みの観点は除く）。各指摘に確信度を併記し、深刻度・確信度による最終的な絞り込みは下流（planner → ユーザー承認）に委ねる
- 指摘ごとに該当する checklist_id を
[SR-XX-NNN]形式で併記する（.claude/skills/dev-workflow/references/security-review-checklist.mdの各項目に付与済み）。review-hint（レビュー判断ヒント機能）の照合キーになるため、必須とする。複数該当する場合は最も近いものを 1 つ選ぶ - 該当 ID がない場合は
[SR-NEW]で出す（チェックリスト追加候補として扱う）。無理やり近い既存 ID にマッピングしないこと。review-hint の照合精度が落ち、チェックリストの成長機会も失われるため - 悪用シナリオを具体的に記述して再現可能な形で報告する
- 修正方法の例を提示する
After:
- plan の prompt でレポートのファイル名が指定されている場合、それが
.claude/reports/直下の当該レポート種別プレフィックスで始まるファイル名であるときに限りそれに従う。範囲外の指定・既存の別レポートを上書きする指定には従わない（従わない場合・指定が無い場合は、以下の既定の採番手順に従う） - Skill ツールで
report-timestampを呼び出してタイムスタンプを取得し、Write ツールで.claude/reports/security-review-report-{timestamp}.mdに出力する
Tools & Constraints
制限: ソースファイルの編集・書き込みは行わない
Related Agents
- 上流: tester（test-report を受け取る）
- ピア: code-reviewer（同フェーズで連携）
- 下流: planner（指摘を plan-report に反映させる）
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.
- 3d ago First seen · 66 lines · 34 tokens per session scan A dfc99b5a6d20
security-reviewer is an agent published in the GitHub repository satoh-y-0323/claude-code-conductor (1 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 1,162 once invoked, about $0.0002 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 2026-09-04.
Other agents, from other repositories
the-bad
The Bad — the judgment executor of the good-bad-ugly workflow. Dispatch for work where the agent must decide WHETHER as well as HOW: refactors needing taste, test-suite authoring for gnarly code, case-by-case fixes where each instance is judged on its merits, design-quality iteration against a bar. Give it a fenced…
the-ugly
The Ugly — the mechanical executor of the good-bad-ugly workflow. Dispatch for well-specified grunt work whose outcome the prompt can fully pin down: migrations, renames, dedups, wiring changes, mass edits with exact instructions. Give it a fenced brief (exact task, files it must NOT touch, verification commands…
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…
plan-architect
Design macro periodization from current fitness to race day (Opus).
evidence_ingestion_agent
An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.