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 ch015/code-pentester --skill pentestgit clone --depth 1 https://github.com/ch015/code-pentesterWrote 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/ch015/code-pentester/pentest)<a href="https://agentmods.dev/skills/ch015/code-pentester/pentest"><img src="https://agentmods.dev/badge/skills/ch015/code-pentester/pentest/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/ch015/code-pentester/pentest"><img src="https://agentmods.dev/badge/skills/ch015/code-pentester/pentest.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 | $0.02033 |
| Opus 5.5 | $0.00014 | $0.00813 |
| Sonnet 5.5 | $0.00007 | $0.00407 |
| Haiku 4.5 | $0.00003 | $0.00203 |
Grade A, and why
ch015-pentest scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- "검증 결과에 실제 curl 명령 + 응답을 증거로 기록" How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
모의해킹 (Penetration Testing) Skill
대상 프로젝트의 소스코드를 공격자 관점에서 분석하여 시나리오 기반 취약점 탐색, POC 생성, 선택적 라이브 검증을 수행합니다.
신규 후보와 검증 결과는 분석 계약을 따른다. 새 후보에는 reasoning v3의 사실·미검증 조건·다음 확인·확정/반증 기준을 기록하고, 기존 후보 검증 시 계약을 보존·갱신한다. 코드 수준 입증, 생성한 POC, 실제 실행한 POC는 구분한다. 실행하지 않은 시나리오를 CONFIRMED로 표기하거나 미검증 조건을 삭제하지 않는다.
서비스 개요
| 항목 | 내용 |
|---|---|
| 서비스명 | 모의해킹 (Pentest) |
| 방법론 | 시나리오 기반 공격 + 방법론 기반 분석 |
| 출력물 | 취약점 상세 + 6-step 영향도 분석 + POC 코드 + 라이브 검증 결과 |
| 코드 수정 | ❌ 없음 (읽기 전용) |
설계 원칙: 방법론 기반 + 공격자 사고
분석 원칙: 방법론, 패턴이 아님
Principles:
No_Pattern_Lists: |
"특정 프레임워크 구문, grep 패턴, 시크릿 접두사 목록에 의존하지 않는다.
이런 목록은 닫힌 집합이며, 목록에 없는 위험을 구조적으로 놓친다."
Use_Methodology: |
"행위(무엇이 일어나는가)를 질문하고, AI가 감지된 기술 스택에 맞는
구체적 코드 패턴을 자율적으로 판단하여 탐색한다."
Attacker_Mindset: |
"방어자가 아닌 공격자 관점으로 코드를 읽는다.
'이 기능이 안전한가'가 아니라 '이 기능을 어떻게 악용할 수 있는가'를 질문한다."
Representative_Examples: |
"안티패턴/올바른 패턴은 '대표적 예시'로만 제시.
분석은 이 예시에 한정되지 않으며 — 동일한 구조적 이슈를 가진
모든 변형이 탐지되어야 한다."
Phase 구조
Phase 0: Recon → 공통 정찰 (common/recon.md 참조)
Phase 0.5: Binding → 정찰 → 분석 컨텍스트 바인딩
Phase 1: Architecture → 8대 아키텍처 차원 리뷰 + 공격 확장 (M9, M10)
Phase 2: Deep Analysis → 원칙 기반 심층 분석 + 공격 체인
Phase 3: Attack → 공격 카테고리 시나리오 분석
Phase 3.5: Creative → 체크리스트 외 프로젝트 고유 공격 추론
Phase 3.8: Routing Plan → Pentest Routing Plan (시나리오 → Route A~F 배정)
Phase 4: POC → 검증 가능한 POC 코드 생성
Phase 4.5: Self-Verify → 분석 결과 자체 검증 (도달 가능성, 보상 제어, 전제조건 분석, 로컬 PoC)
Phase 6.0: Sweep → 승인 범위 기반 엔드포인트 스윕 (--url 옵션 시, Finding 무관)
Phase 6: Live → Finding 기반 라이브 검증 (--url 옵션 시)
Phase 5: Report → 종합 보고서 + 6-step 영향도 분석 + 전제조건 포괄 그룹
Phase 5R: Regulatory → 규제 영향 참조 (Finding 기반, 해당 시에만)
실행 순서 주의: Phase 5(Report)는 번호와 달리 최종 단계다 —
--url옵션 시 Phase 6.0/6 라이브 검증 결과를 반영한 후 pentest-report.template.md 기반으로 보고서를 생성하고, Phase 5R(규제 영향 참조)을 말미에 첨부한다. Phase 5는 별도 본문 섹션 없이 위 산출 규칙과 템플릿으로 수행한다.
What ships with it
14 files 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.
- references/architecture.md 6.2 KB
- references/attack-categories.md 13 KB
- references/attack-chains.md 2.5 KB
- references/creative-reasoning.md 3.9 KB
- references/endpoint-sweep.md 12 KB
- references/finding-structure.md 2.7 KB
- references/live-evidence.md 7.2 KB
- references/live-interaction.md 7.6 KB
- references/live-requests.md 976 B
- references/live-routing.md 10 KB
- references/poc.md 1.5 KB
- references/regulatory.md 1.2 KB
- references/routing-plan.md 5.7 KB
- references/self-verification.md 4.8 KB
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.
- 4d ago Changed 39ef5b1b1e96
- 1mo ago Changed · -1,439 lines scan B → A 902dea09ab26
- 1mo ago First seen · 1,570 lines · 35 tokens per session scan B 4bc7c55ef032
ch015-pentest is a skill published in the GitHub repository ch015/code-pentester (4 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 2,033 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dekko-verify
Sanity-check a suspiciously low or zero call-graph result from dekko (getcallers, getcallees, findusages, impactedtests, unused) before concluding "no callers" or "dead code," or a heritage/throws-provenance result (query supertypes, query subtypes, query throws) that labels something (external) when you expect it to…
dekko-review-context
Give a code-review or PR-description flow a structural head start before reading a diff line by line. Trigger when the user asks for a PR description, a pre-merge summary, or invokes a code-review flow (/code-review, /review, or an equivalent) against a diff in a repo with a .dekko/ directory.
codeweb
Inspect mapped callers and impact before changing code, find existing implementations before adding one, and review structural changes after an edit. Use during coding tasks; Codeweb product planning uses a separate workflow.
analyze
A codebase analysis workflow for existing projects. It explores the code, adds outside research, and produces a Markdown report about architecture, technical debt, security, performance, and possible improvements.
braintrust
An in-session review panel that has several independent agents examine a design, plan, policy, or decision from different critical viewpoints. It reviews the material already discussed in the current conversation and combines the findings.
review-pr
Visualize a pull request on the Cartographer map — see which entities are affected, the blast radius, and the review path. Use when user says "review pr", "review pull request", or "/cartographer review-pr".