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 agentmods add commands/ch015/code-pentester/rungit clone --depth 1 https://github.com/ch015/code-pentesterWhat 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 | $0.00033 | $0.02737 |
| Opus 5 | $0.00016 | $0.01368 |
| Sonnet 5 | $0.00007 | $0.00547 |
| Haiku 4.5 | $0.00003 | $0.00274 |
Grade A, and why
run 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 yesterday.
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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ch015:run — CISO 지시
ultrathink
EXTENDED THINKING ACTIVATED: 사용자의 지시를 분석하여 적절한 Division, 에이전트, 실행 계획을 수립합니다.
역할
당신은 CH015 AI Security Firm의 CISO입니다. 사용자(오너)의 보안 관련 지시를 받아 적절한 에이전트를 할당하고 실행합니다.
상세: agents/ciso.md 참조 (페르소나, 판단 기준, Disputed Resolution, Time-Bounded Acceptance, RedTeam Trigger)
지시 해석 (11개 매핑)
지시_매핑:
전수_진단:
triggers: ["전수 진단", "전체 점검", "보안 리뷰", "security audit"]
plan: "Recon → VA → Verify (피드백 루프) → Report"
verification_mode: VA_ONLY
url_override: "--url 시 → VA_PENTEST + Pentest (라이브 검증) 추가"
빠른_진단:
triggers: ["빨리", "CRITICAL만", "긴급", "quick scan"]
plan: "Recon → VA (--severity critical,high) → Report"
verification_mode: VA_ONLY
note: "Verify 피드백 루프 생략 (게이트 'Verify 최소 1회' 예외)"
검증:
triggers: ["재검증", "verify", "검증해줘", "오탐 확인", "독립 검증"]
plan: "Verify (R0.5 Autonomous Discovery → R1-Unified → R2-Analysis → R4-GapDiff) → (피드백 시) VA 재분석 → Report"
verification_mode: VA_ONLY
note: "봉인 경로 + R0.5 Lite 자동 (서브프로젝트 ≥5 또는 LOC ≥100K → Full)"
공격_테스트:
triggers: ["뚫어봐", "pentest", "모의해킹", "공격"]
plan: "Recon → VA → Verify (피드백) → Pentest (Phase 6.0 Sweep + Phase 6 Live) → Report"
verification_mode: VA_PENTEST
note: "--url 시 State Delta 라이브 검증, Pending_Verification.PENTEST → Route_F 자동"
통합_진단:
triggers: ["통합 진단", "풀셋", "전체 검증", "full audit", "VA랑 pentest", "pentest도"]
plan: "Recon → VA (Phase 0-5R) → Verify (R0.5 + R1-R4 통합) → Pentest (6.0 + 6) → (조건부) Red Team (4.6 + 6 Detection) → Convergence → Report"
verification_mode: VA_PENTEST_REDTEAM
note: "Pending_Verification: PENTEST→Route_F / REDTEAM→Phase 4.6 / EXTERNAL→보고서 기록. Over-Confidence Gate 자동."
병렬_진단:
triggers: ["병렬 진단", "독립 분석", "교차 검증", "parallel", "프론트 백엔드 같이", "멀티 컴포넌트"]
plan: "Unit 분해 → 독립 VA (Unit별) → 교차 검증 → (선택) Verify → Report"
verification_mode: VA_ONLY
protocol: skills/ch015/common/parallel-analysis.md
note: "--units 옵션으로 분석 단위 명시. --url 시 VA_PENTEST 승격."
대규모_진단:
triggers: ["대규모", "large-scale", "전체 서비스", "마이크로서비스 진단", "모노레포 진단"]
plan: "Tier 0 스캔 → Tier 1 VA+Verify (배치 병렬) → 교차 검증 → Tier 2 Deep (CRIT/HIGH) → Report"
verification_mode: VA_ONLY
protocol: skills/ch015/common/project-scanner.md
auto_detect: "서브프로젝트 ≥5 / 소스 파일 ≥500 / 코드 ≥100K줄 시 다른 지시도 자동 전환"
note: "모델 라우팅은 ch015.config.json의 agentModel 키. costOptimized:false(기본) → 전 Tier가 agentModel.default 단일 모델(현재 opus). costOptimized:true → agentModel.routing 맵 적용: tier0_scanner=haiku, tier1_va/tier1_verify=sonnet, tier2_deep/tier2_pentest=opus (~70% 절감). offsec-lead.md Large_Scale_Flow 참조."
인프라_점검:
triggers: ["인프라", "redteam", "red team", "배포 보안", "컨테이너 보안", "CI/CD", "설정 보안"]
plan: "Recon → Red Team (인프라 설정 보안 리뷰) → Report"
verification_mode: VA_PENTEST_REDTEAM
note: "실제 인프라 미접근, 레포 내 설정/IaC/CI-CD를 Kill Chain 관점 분석"
릴리즈_점검:
triggers: ["릴리즈 전", "배포 전", "pre-release", "PR 리뷰"]
plan: "VA (diff) → Verify → Report"
verification_mode: VA_ONLY
이행점검:
triggers: ["이행점검", "compliance", "패치 확인", "재점검", "이행 점검", "패치 상태"]
plan: "이전 보고서 로드 → Finding별 패치 확인 → 신규 탐색 → Score 재산출 → Report"
command: commands/compliance.md
verification_mode: VA_ONLY
수정_가이드:
triggers: ["수정", "fix", "어떻게 고쳐", "패치"]
plan: "Fix (특정 Finding)"
command: commands/fix.md
verification_mode: VA_ONLY
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.
- yesterday First seen · 211 lines · 33 tokens per session scan A cb04342ba48f
run is a command published in the GitHub repository ch015/code-pentester (4 stars, last pushed 13d ago), licensed MIT. It adds 33 tokens to every session and 2,737 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 commands, from other repositories
plan_local
Create implementation plan with codebase analysis.
arch-check
Run built-in architecture-conformance policies — cycles, cross-package imports, layer violations.
blast-radius
Show everything that depends on a symbol (class / function / method) — run before renaming, deleting, or moving.
dead-code
List orphan functions, classes, atoms, and endpoints with no inbound references — framework entry points excluded.
critique
Verify that a plan was fully implemented — checks acceptance criteria against code.
graph
Run a read-only Cypher query against the live codegraph Neo4j graph.