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 vagit 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/va)<a href="https://agentmods.dev/skills/ch015/code-pentester/va"><img src="https://agentmods.dev/badge/skills/ch015/code-pentester/va/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/va"><img src="https://agentmods.dev/badge/skills/ch015/code-pentester/va.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 | $0.00037 | $0.01642 |
| Opus 5.5 | $0.00015 | $0.00657 |
| Sonnet 5.5 | $0.00007 | $0.00328 |
| Haiku 4.5 | $0.00004 | $0.00164 |
Grade A, and why
ch015-va 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 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.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
취약점 진단 (Vulnerability Assessment) Skill
대상 프로젝트의 소스코드를 아키텍처 차원 기반으로 체계적으로 점검하여 보안 메커니즘의 구현 현황과 미적용 영역을 식별합니다.
서비스 개요
| 항목 | 내용 |
|---|---|
| 서비스명 | 취약점 진단 (VA) |
| 방법론 | 아키텍처 차원 기반 + 방법론 중심 분석 |
| 출력물 | 아키텍처 차원 건강도 + 취약점 목록 + 6-step 영향도 분석 + 표준 준수 현황 |
| 코드 수정 | ❌ 없음 (읽기 전용) |
설계 원칙: 아키텍처 차원 + 방법론 기반 분석
OWASP/CWE는 보고서의 참조 태깅으로만 사용합니다. 분석의 조직 원리는 8대 보안 아키텍처 차원입니다.
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.
예: '사용자 입력이 문자열 연결로 쿼리에 삽입되는가?'라고 질문하되
어떤 언어 구문을 찾을지는 AI가 판단."
Representative_Examples: |
"안티패턴/올바른 패턴은 '대표적 예시'로만 제시.
분석은 이 예시에 한정되지 않으며 — 동일한 구조적 이슈를 가진
모든 변형이 탐지되어야 한다."
No_Library_Assumptions: |
"라이브러리의 존재, 이름, 일반적 평판으로 보안 속성을 추론하지 않는다.
'라이브러리가 X를 할 수 있다' ≠ '이 프로젝트에서 X가 작동하고 있다.'
프로젝트의 실제 설정과 resolved version의 라이브러리 소스/공식 문서를 대조하여
적용되는 기본 보안 속성까지 확인한다. 옵션 생략만으로 방어 부재를 판단하지 않는다.
확인 불가능하면 '미확인(Unverified)'으로 보고하고,
미적용 시 영향을 함께 기술한다."
Phase 구조
Phase 0: Recon → 공통 정찰 (common/recon.md 참조)
Phase 0.5: Binding → 정찰 → 분석 컨텍스트 바인딩
Phase 0.8: AST Pre-Analysis → Tree-sitter + Semgrep 구조 분석 (--mode ast 지정 시)
Phase 1: Architecture → 8대 보안 아키텍처 차원 리뷰
Phase 2: Deep Analysis → 원칙 기반 심층 분석
Phase 3: Compliance → 보안 표준 준수 점검
Phase 3.5: Self-Verify → 분석 결과 자체 검증 (도달 가능성, 보상 제어, 경량 공격 체인)
Phase 4: Scoring → 보안 점수 산출 (Self-Verify 결과 반영, Self-Verify Gate 통과 필수)
Phase 4.5: Evidence Verify → file:line 증거 독립 검증 (common/evidence-verification.md)
Phase 4.7: Raw Ledger → Raw Findings Ledger + Pentest Plan 초안 생성 (Phase 5 진입 게이트)
Phase 5: Report → 종합 보고서 + 6-step 영향도 분석
Phase 5.1: Index → Findings Index YAML 생성 (하류 에이전트 컨텍스트 최적화)
Phase 5B: Baseline → Baseline Snapshot 생성 (이행점검 기준선, full audit 시에만)
Phase 5R: Regulatory → 규제 영향 참조 (Finding 기반, 해당 시에만)
What ships with it
31 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.
- checklists/api.yaml 20 KB
- checklists/db-layer.yaml 6.6 KB
- checklists/native-client.yaml 8.3 KB
- checklists/web-app.yaml 11 KB
- compliance.md 4.2 KB
- concurrency.md 7.0 KB
- deep-analysis.md 6.4 KB
- depth/access-control.md 2.8 KB
- depth/auth-bypass.md 2.9 KB
- depth/concurrency.md 2.5 KB
- depth/crypto-misuse.md 2.4 KB
- depth/data-flow.md 2.9 KB
- depth/injection.md 5.8 KB
- depth/ssrf.md 6.7 KB
- principles/baas-trust-boundary.md 2.5 KB
- principles/oauth-provider-misconfig.md 2.3 KB
- principles/row-level-security.md 2.3 KB
- principles/webhook-integrity.md 2.1 KB
- references/architecture.md 4.8 KB
- references/ast-preanalysis.md 6.7 KB
- references/baseline.md 2.3 KB
- references/evidence.md 1.8 KB
- references/finding-structure.md 6.7 KB
- references/handoff.md 3.1 KB
- references/ledger.md 7.8 KB
- references/regulatory.md 1.1 KB
- references/report.md 4.7 KB
- references/scoring.md 11 KB
- references/self-verification.md 25 KB
- regulatory.md 16 KB
- supply-chain.md 6.2 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 5a7e841a7cc9
- 1mo ago Changed · -1,248 lines e444ac18d8ee
- 1mo ago First seen · 1,353 lines · 37 tokens per session scan A 9548bfb02776
ch015-va is a skill published in the GitHub repository ch015/code-pentester (4 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 1,642 once invoked, about $0.0001 per session on Opus 5.5. 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
ai-code-generation-guardrails
Use when reviewing AI-generated code before merge or execution: plan AST/security checks, isolated behavior tests and evidence, with language-specific coverage limits.
windows-compat
Audit and harden this Rust repo (code-graph-mcp) for Windows correctness: path-spelling drift between producers, the 32,767-char command-line cap, index-key mismatches, and path predicates that assume one ecosystem's layout. Use whenever touching code that builds, compares, prints, or stores a filesystem path; that…
index
Diagnose and fix code-graph index issues. Use when: search returns unexpected/empty results, or after major codebase restructuring. Covers the health check and both rebuild paths from the CLI.
explore
Understand code structure with the AST index before reading files one by one — when starting work in unfamiliar code, exploring a module before a change, or finding which file to edit. An overview lists a directory's symbols and their callers in one call.
setup-agent-guard
Diagnose, install, and verify Agent Guard's plugin-local binary, jq and gitleaks dependencies, the active host integration, and live hook protection. Use when Agent Guard reports degraded protection, a SessionStart warning asks for setup, plugin hooks fail or appear bypassed, or a user asks to finish or repair Agent…
setup-shell
Install or refresh Agent Guard's plugin-local shell integration. Use when the user explicitly asks to enable or update shell command masking, or when a shell-integration warning directs them to rerun setup-shell.