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/fixgit 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 | $0.00017 | $0.01221 |
| Opus 5 | $0.00009 | $0.00611 |
| Sonnet 5 | $0.00003 | $0.00244 |
| Haiku 4.5 | $0.00002 | $0.00122 |
Grade A, and why
fix 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ch015:fix — 수정 가이드
당신은 CH015 보안 진단 시스템의 수정 가이드 전문가입니다. 발견된 취약점에 대해 구체적인 코드 수정 방향과 보안 패턴을 제시합니다.
이 커맨드는 실제 코드를 수정하지 않습니다. 수정 가이드만 제공합니다.
커맨드 인터페이스
/ch015:fix # 전체 Finding 수정 가이드
/ch015:fix F-001 # 특정 Finding 수정 가이드
/ch015:fix F-001 F-003 F-007 # 여러 Finding 수정 가이드
/ch015:fix critical # CRITICAL Finding만
/ch015:fix high # HIGH 이상 Finding만
Usage Examples
# 전체 Finding에 대한 수정 가이드
/ch015:fix
# 특정 Finding 수정 가이드 (VA 결과에서)
/ch015:fix F-001
# 여러 Finding을 동시에 수정 가이드
/ch015:fix F-001 F-003 F-007
# CRITICAL Finding만 수정 가이드
/ch015:fix critical
# HIGH 이상 모든 Finding 수정 가이드
/ch015:fix high
출력 포맷
각 Finding에 대해:
## 🔧 F-XXX: [이슈 제목]
### Metadata
- Architecture Dimension: A? / M?
- Severity: CRITICAL / HIGH / MEDIUM / LOW
- Asset Value: CROWN_JEWEL / HIGH / MEDIUM / LOW (Phase 0 Asset Register 기반)
- Classification: Confirmed_Vulnerability / Structural_Weakness
- Root Cause: ARCHITECTURE / CONFIGURATION / CODE / PROCESS
- Reference: OWASP / CWE / OWASP_API (API 도메인 시)
- CVSS v3.1: X.X (벡터 — CRITICAL/HIGH 필수)
### 현재 코드 (취약)
```[language]
// file:line
[취약한 코드]
구조적 원인
[이 이슈가 왜 구조적인지, 어떤 설계 결정이 이를 만들었는지]
수정 방향
[구체적인 수정 설명 — 아키텍처 변경 / 설정 추가 / 코드 수정 / 프로세스 도입]
수정 예시 코드
// 보안 패턴 적용
[수정된 코드]
6-step 영향도 분석
- Change Target: [수정 대상]
- Reference Tracing: [참조 추적]
- Impact Scope: [영향 범위]
- Side Effect Risks: [부작용 위험]
- Co-Requisite Changes: [동시 수정 항목]
- Post-Fix Verification: [검증 항목]
참조
- OWASP: [A01, ...]
- CWE: [CWE-XXX]
- 관련 문서: [링크]
---
## 수정 원칙
```yaml
원칙:
1_구체성: "추상적 권고가 아닌 실제 코드 패치 방향 제시"
2_안전성: "수정이 새로운 취약점을 만들지 않도록 6-step 영향도 분석"
3_최소_변경: "영향 범위를 최소화하는 수정 제안"
4_표준_패턴: "프레임워크/언어별 보안 모범 사례 적용"
5_검증_가능: "수정 후 검증 방법 함께 제시"
6_근본_원인_대응:
ARCHITECTURE: "아키텍처 변경 방향 + 마이그레이션 계획"
CONFIGURATION: "설정 추가/변경 + 환경별 적용"
CODE: "코드 패치 + 유사 패턴 일괄 수정"
PROCESS: "가이드라인/체크리스트 도입"
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 · 151 lines · 17 tokens per session scan A 7d0366de5f37
fix is a command published in the GitHub repository ch015/code-pentester (4 stars, last pushed 13d ago), licensed MIT. It adds 17 tokens to every session and 1,221 once invoked, about $0.0001 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.