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.
git 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/commands/sodam-ai/sodam-reverse-eng/re-binary)<a href="https://agentmods.dev/commands/sodam-ai/sodam-reverse-eng/re-binary"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-reverse-eng/re-binary/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/commands/sodam-ai/sodam-reverse-eng/re-binary"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-reverse-eng/re-binary.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 | $0.00040 | $0.00738 |
| Opus 5.5 | $0.00016 | $0.00295 |
| Sonnet 5.5 | $0.00008 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
re-binary 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 1mo 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-binary — 바이너리 역공학 분석
분석 대상 (EXE/DLL/SO 등): $ARGUMENTS
re-analyze-binary 스킬의 순서를 그대로 따르세요:
- 안전 스코프(1층) — 크랙·우회·추출 요청이면 보고서 대신 즉시 거부 + 방어적 대안 제안.
- 동의 게이트(강화) — ① 본인 소유/허가? ② 방어·학습 목적(크랙·우회 안 함)? ③ 책임은 사용자? 하나라도 '아니오'/무응답 → 중단.
- 도구 확인 — Ghidra·JDK 21+(2026-08-19 실측 정정: Ghidra 12.1.3부터 요구 버전 상승) 설치 확인. 없으면 Python+LIEF(경량 대안, 디스어셈블은 불가하나 설치 마찰 적음, §2-2)로 대체 제안. 셋 다 없으면 설치 안내만 하고 분석 시작 안 함(fail-closed). IDA는
SODAM_RE_IDA_PATH설정 시 옵션. - 정적 분석 — 읽기 전용, 인자 배열(주입 방지), 대상 실행 금지. 악성코드 의심 시 거부.
- 표준 한국어 보고서 — 한 줄 요약·파일개요·함수목록·문자열/임포트·근거 위치·불확실한 점·다음 확인사항·⚠️ 안전.
- 저장 —
./.sodam-re/binary/로컬 전용.
안전 경계
| 요청 | 결과 |
|---|---|
| "내가 만든 exe 어떻게 동작하는지 알고 싶어" | ✅ 동의 후 진행 |
| "이 DLL이 어떤 API 쓰는지 알려줘" | ✅ 동의 후 진행 |
| 크랙·우회·키 추출 방법 | 🛑 1층 거부 |
| 악성코드 의심 파일 | 🛑 이번 범위에 없음 — 분석 거부(정책검토 대기) |
| 타사 실행파일 무단 분석 | 🛑 동의 게이트 차단 |
소스레벨이 아닌 정적 바이너리 분석이라 Ghidra+JDK 21+ 설치가 필요합니다. 2026-08-19: Ghidra 12.1.3을 실제로 설치해 headless 분석 명령이 정상 동작함을 환경 차원에서 확인했습니다(CHECKPOINT §5-68). 2026-08-21 갱신:
/sodam-reverse:re-binary슬래시 명령도 실제 Claude Code 세션에서 동의→Ghidra 분석→표준 보고서까지 전 과정 실사용 검증 완료(CHECKPOINT §5-87, 함수 5개 추출 확인 —D:\Test_Dev\test6\.sodam-re\binary\report_sodam_dummy.exe.md실제 보고서 파일로 재확인).
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.
- 1mo ago Changed 405b82a76c51
- 1mo ago First seen · 29 lines · 40 tokens per session scan A f7aed70e57f8
re-binary is a command published in the GitHub repository sodam-ai/SoDam-Reverse-Eng (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 738 once invoked, about $0.0002 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 commands, from other repositories
skill-maker
A guided prompt for designing a new SKILL.md file, which is a reusable instruction set for an AI agent. It turns a user’s idea into the required skill format and includes safety and formatting rules.
long-text-summary
A command that summarizes pasted Korean or other long text into its main points in up to three short lines.
presentation-script
A command that writes a presentation script from a topic and speaking time. It structures the script into an introduction, main section, and conclusion, with spoken wording and stage cues.
explain-simply
A command that explains a difficult concept in simple Korean using one everyday comparison, based on the listener's age or level.
self-intro-polish
A guided writing prompt for turning personal notes into a short self-introduction. It adapts the tone to the intended use, such as a formal application or a friendly social post.
sns-caption
A command that writes two social-media captions and five hashtags from a situation or photo description and a requested mood. The captions include a short and a longer version.