Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add morodomi/redteam-skills --skill context-reviewgit clone --depth 1 https://github.com/morodomi/redteam-skillsWrote 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/skills/morodomi/redteam-skills/context-review)<a href="https://agentmods.dev/skills/morodomi/redteam-skills/context-review"><img src="https://agentmods.dev/badge/skills/morodomi/redteam-skills/context-review/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/skills/morodomi/redteam-skills/context-review"><img src="https://agentmods.dev/badge/skills/morodomi/redteam-skills/context-review.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 | $0.00035 | $0.00911 |
| Opus 5 | $0.00017 | $0.00456 |
| Sonnet 5 | $0.00007 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
context-review 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Review
security-scan結果の曖昧な項目について、ユーザーに質問して確認する対話型スキル。
Usage
/context-review # 直近のsecurity-scan結果をレビュー
/context-review ./scan-result.json # 指定ファイルをレビュー
Workflow
1. ANALYZE Phase
- security-scan結果を読み込み
- 曖昧な検出項目を抽出
- 質問リストを生成
2. QUESTION Phase
- ユーザーに質問を提示
- 選択肢形式で回答を取得
- 1問ずつ確認
3. RESOLVE Phase
- 回答を反映して判定確定
- 結果をJSON出力
- attack-reportへの入力として使用可能
Question Categories
| Category | Description | 質問例 |
|---|---|---|
| auth-intent | 認証要否の意図確認 | 「このAPIは認証不要で正しいですか？」 |
| error-handling | 例外処理の妥当性 | 「本番環境でスタックトレースは無効ですか？」 |
| data-exposure | データ露出の意図確認 | 「このレスポンスに機密情報は含まれますか？」 |
| business-logic | ビジネスロジック検証 | 「この計算ロジックは仕様通りですか？」 |
Question Format
各質問は以下の形式で提示:
### Q1: 認証不要API [auth-intent]
ファイル: app/Http/Controllers/Api/StatusController.php:15
検出: 認証ミドルウェアなし
このAPIは認証不要で正しいですか？
1. はい、公開APIです（脆弱性から除外）
2. いいえ、認証が必要です（脆弱性として報告）
3. わからない（手動レビュー推奨）
Resolution Values
| Value | Meaning | 対応 |
|---|---|---|
| excluded | 意図的、脆弱性でない | レポートから除外 |
| confirmed | 脆弱性として確定 | レポートに含める |
| needs_review | 判断保留 | 手動レビュー推奨としてマーク |
Output Format
{
"metadata": {
"review_id": "<uuid>",
"reviewed_at": "<timestamp>",
"skill": "context-review"
},
"questions": [
{
"id": "Q1",
"category": "auth-intent",
"file": "app/Http/Controllers/Api/StatusController.php",
"line": 15,
"question": "このAPIは認証不要で正しいですか？",
"answer": 1,
"resolution": "excluded",
"reason": "ユーザー確認: 公開API"
}
],
"summary": {
"total_questions": 5,
"excluded": 3,
"confirmed_vuln": 1,
"needs_review": 1
}
}
Integration
With security-scan
# 1. スキャン実行
/security-scan ./src
# 2. コンテキストレビュー（対話型）
/context-review
# 3. レポート生成
/attack-report
With false-positive-filter
context-reviewはfalse-positive-filterと補完関係:
| スキル | 方式 | 対象 |
|---|---|---|
| false-positive-filter | パターンマッチ | 明確な誤検知 |
| context-review | ユーザー確認 | 曖昧な項目 |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 126 lines · 35 tokens per session scan A 2b7ae3341b4e
context-review is a skill published in the GitHub repository morodomi/redteam-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 35 tokens to every session and 911 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 2026-08-31.
Other skills, from other repositories
security-expert
Expert-level application security, OWASP Top 10, penetration testing, and security best practices. Use when the user mentions OWASP, pentesting, appsec, vulnerability, encryption, or authentication, or when the task involves Security Principles, OWASP Top 10, Security Domains, or Broken Access Control.
api-secure-report
Full security inventory of every HTTP route in a backend project — each route marked clean or carrying findings, with the exploitation path and the mitigation, written in the user's language (pt-BR by default). Use when the user runs /api-secure-report, or asks for a security report, audit or inventory of the…
penetration-tester
Authorized penetration tester persona — offensive security specialist for network, web app, cloud, and Active Directory assessments. Requires explicit authorization.
Mixed-Language Monorepos
This skill should be used when the user is auditing a "polyglot monorepo", "multi-language codebase", "microservices with different languages", "Go + Python + TypeScript", or any codebase with services written in different programming languages. Provides strategies for cross-service security analysis and unified…
OWASP API Security Top 10
This skill should be used when the user asks about "API security", "OWASP API Top 10", "BOLA", "broken object level authorization", "API authentication", "mass assignment", "GraphQL security", "gRPC security", "rate limiting", "API abuse", "REST API vulnerabilities", or needs to identify API-specific security issues…
Cache Poisoning
This skill should be used when the user asks about "cache poisoning", "web cache deception", "CDN cache", "proxy cache", "nginx cache", "varnish", "cache key manipulation", "response caching", or needs to find cache-related vulnerabilities during whitebox security review.