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 sodam-ai/SoDam-Reverse-Eng --skill re-analyze-mycodegit clone --depth 1 https://github.com/sodam-ai/SoDam-Reverse-EngWrote 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/sodam-ai/sodam-reverse-eng/re-analyze-mycode)<a href="https://agentmods.dev/skills/sodam-ai/sodam-reverse-eng/re-analyze-mycode"><img src="https://agentmods.dev/badge/skills/sodam-ai/sodam-reverse-eng/re-analyze-mycode/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/sodam-ai/sodam-reverse-eng/re-analyze-mycode"><img src="https://agentmods.dev/badge/skills/sodam-ai/sodam-reverse-eng/re-analyze-mycode.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 | $0.00061 | $0.00741 |
| Opus 5 | $0.00030 | $0.00370 |
| Sonnet 5 | $0.00012 | $0.00148 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
re-analyze-mycode 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.
What it actually says
re-analyze-mycode — 내 코드/앱 분석 (MVP)
전제: re-router의 동의 게이트를 이미 통과했어야 한다. 안 했으면 먼저 동의부터 받는다.
안전 (1층 — 항상 적용)
- 크랙·우회·인증분기 위치 지목·키/토큰 추출 요청은 출력 거부(re-router 0번 규칙 그대로).
- 코드의 '안전/위험'을 단정하지 않는다. 의심돼도 "단정 불가 — 전문가 확인 필요"로 표현.
- 분석 중 시크릿(키·토큰·비밀번호)을 발견하면 보고서·로그에 평문으로 쓰지 말고 마스킹한다 (
references/mask-patterns.json참조). 매칭된 문자열 전체를mask-patterns.json의_mask_with(••••(마스킹됨)) 값으로 완전히 치환한다 — 앞/뒤 일부 글자도 남기지 않는다(예:sk-a••••7890처럼 접두/접미를 남기는 부분 마스킹 금지). 출력 직전 재확인: 보고서를 내보내기 전 마스킹한 값을 한 번 더 훑어, 원본 글자가 앞/뒤 어디든 하나라도 남아 있으면 그 값 전체를 다시 완전히 치환한다(2026-08-13 라이브 테스트에서 접두/접미 잔존 사례 발견 후 추가).
작업 규칙 (DO NOT)
- 분석 대상을 실행하지 마라. 읽기 전용이다.
- 대상 경로에
..·심볼릭 링크·동의 범위 밖 접근이 있으면 거부한다(경로 조작 방지). - 외부 분석기를 쓸 일이 생겨도(P2+) 사용자 입력을 셸 문자열로 연결 금지 — 인자 배열로 전달.
- 자체 RE 엔진을 새로 만들지 마라. (MVP는 소스 직접 읽기로 충분)
비용 보호 (토큰 가드)
분석 전 대상 크기를 가늠한다. 크면(예: 수십 파일/수천 줄) 먼저 제안한다: "예상 사용량이 큽니다. 파일/폴더 단위로 나눠 진행할까요?"
분석 절차
- 대상(파일/디렉터리) 범위 확인 — MVP는 소스 코드 전용(빌드 산출물·바이너리·APK는 P2/P3).
- 소스를 읽고 구조 파악: 진입점 → 주요 함수 → 데이터 흐름 → 외부 호출/의존성.
- 근거 기록: 모든 주장에
파일:라인을 붙인다. (정확성 게이트 — 실제 코드와 일치해야 함, 환각 금지) - 불확실한 점("추정")과 확인된 사실("확인됨")을 분리한다.
- 결과를
re-report표준 형식으로 출력한다.
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 · 34 lines · 61 tokens per session scan A 43eae9b81495
re-analyze-mycode is a skill published in the GitHub repository sodam-ai/SoDam-Reverse-Eng (4 stars, last pushed 8d ago), licensed Apache-2.0. It adds 61 tokens to every session and 741 once invoked, about $0.0003 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
skill-maker
A Korean-language helper for designing a new SKILL.md file through conversation. It creates the completed skill instructions with a small number of user inputs and a specified output format.
study-planner
A Korean-language study-planning guide that creates a weekday-based timetable from a subject, goal, and time period. It includes daily tasks, estimated study time, and regular review.
book-report-helper
A Korean-language helper that writes three-paragraph book reports for elementary or middle-school students from a book title and the student’s impressions.
explain-simply
An explanation helper that uses one everyday comparison to make a difficult idea easier for a specified age group to understand.
long-text-summary
A short-summary skill that extracts the main points from pasted writing and returns up to three brief lines.
natural-english
A Korean-to-English writing helper that turns a Korean sentence into natural English and briefly explains the wording.