re-binary

re-binary is a command for Claude Code from sodam-ai/SoDam-Reverse-Eng. It costs 40 tokens per session (738 once invoked), scanned A, original, Apache-2.0.

A command for starting static analysis of an executable file such as an EXE, DLL, or SO. Static analysis examines a file without running it.

In plain words
What is it for?
Use it to inspect authorised software with tools such as Ghidra, list functions, strings, and imported APIs, and create a Korean report.
Why use it?
It adds ownership and safety checks and avoids executing the target, while documenting what can and cannot be confirmed.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions Claude Code.

Part of the sodam-reverse plugin — 6 skills, 7 commands, 1 hook shipped together

Install

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.

agentmods
npx agentmods add commands/sodam-ai/sodam-reverse-eng/re-binary
Clone the repo
git clone --depth 1 https://github.com/sodam-ai/SoDam-Reverse-Eng

Made for: Claude Code.

Or install sodam-reverse, the plugin that ships this one along with the rest of its 6 skills, 7 commands, 1 hook.

Wrote 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.

agentmods badge for re-binary

README.md
[![agentmods](https://agentmods.dev/badge/commands/sodam-ai/sodam-reverse-eng/re-binary.svg)](https://agentmods.dev/commands/sodam-ai/sodam-reverse-eng/re-binary)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 738 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.00738
Opus 5 $0.00020 $0.00369
Sonnet 5 $0.00008 $0.00148
Haiku 4.5 $0.00004 $0.00074

Measured today against content hash 405b82a76c51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 today.

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.

commands/re-binary.md · 29 lines

What it actually says

/re-binary — 바이너리 역공학 분석

분석 대상 (EXE/DLL/SO 등): $ARGUMENTS

re-analyze-binary 스킬의 순서를 그대로 따르세요:

  1. 안전 스코프(1층) — 크랙·우회·추출 요청이면 보고서 대신 즉시 거부 + 방어적 대안 제안.
  2. 동의 게이트(강화) — ① 본인 소유/허가? ② 방어·학습 목적(크랙·우회 안 함)? ③ 책임은 사용자? 하나라도 '아니오'/무응답 → 중단.
  3. 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_PATH 설정 시 옵션.
  4. 정적 분석 — 읽기 전용, 인자 배열(주입 방지), 대상 실행 금지. 악성코드 의심 시 거부.
  5. 표준 한국어 보고서 — 한 줄 요약·파일개요·함수목록·문자열/임포트·근거 위치·불확실한 점·다음 확인사항·⚠️ 안전.
  6. 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-binary 슬래시 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.md 실제 보고서 파일로 재확인).

Changes

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.

  1. today Changed 405b82a76c51
  2. 5d ago First seen · 29 lines · 40 tokens per session scan A f7aed70e57f8

Subscribe to this mod's changes

re-binary is a command published in the GitHub repository sodam-ai/SoDam-Reverse-Eng (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 40 tokens to every session and 738 once invoked, about $0.0002 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.