Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add sodam-ai/SoDam-Reverse-Eng/plugin install sodam-reverseWrote 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-start)<a href="https://agentmods.dev/commands/sodam-ai/sodam-reverse-eng/re-start"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-reverse-eng/re-start/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-start"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-reverse-eng/re-start.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 | $0.00025 | $0.01566 |
| Opus 5 | $0.00013 | $0.00783 |
| Sonnet 5 | $0.00005 | $0.00313 |
| Haiku 4.5 | $0.00003 | $0.00157 |
Grade A, and why
re-start 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 5d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SoDam-Reverse 안전 분석 시작
즉시 거부 대상 (아래 요청이 오면 분석하지 말고 거부): 크랙, DRM 우회, 인증 우회, 라이선스 우회, 키추출, 비밀번호 추출
분석 대상: $ARGUMENTS
아래 단계를 순서대로 반드시 따르세요. 건너뛰지 마세요.
0단계: 안전장치 자가검증 (3층 무결성 — 필수, 건너뛰지 마세요)
Bash로 다음을 실행하세요:
node "${CLAUDE_PLUGIN_ROOT}/hooks/_selftest.mjs"
결과에 ❌가 하나라도 있으면 다음 단계로 진행하지 말고 즉시 중단하고, 실패 항목을 사용자에게 보여주며 재설치·복구를 안내하세요(fail-closed — 변조 의심 상태로 동의·분석을 진행하지 않습니다).
1~3단계: 동의 확인 (번호 선택 — 자연어 "예/아니오" 타이핑 요구 금지)
AskUserQuestion 도구로 아래 3개 질문을 한 번에 물어보세요(re-android·re-binary와 동일한 3문항 구조로 통일, 2026-07-27). 사용자가 "예"/"아니오"를 직접 타이핑하게 하지 말고, 반드시 선택지를 눌러 고르는 형태로 제시하세요:
-
질문 1 (header: "소유권") — "이 파일/코드는 본인이 직접 만들었거나, 분석 권한을 가진 것이 맞나요?"
- 옵션: "예, 맞습니다" / "아니오"
-
질문 2 (header: "분석 목적") — "이 분석은 방어·교육 목적이 맞나요?"
- 옵션: "예, 맞습니다" / "아니오"
-
질문 3 (header: "이용 동의") — "분석 결과를 방어·학습·본인 소유물 목적으로만 쓰고, 불법 활동(크랙·우회·키추출)에 쓰지 않겠다는 데 동의하나요?"
- 옵션: "예, 동의합니다" / "아니오"
-
세 질문 모두 "예" 계열 선택 → 4단계 진행
-
하나라도 "아니오" 선택 또는 응답 거부 → 즉시 중단: "동의가 확인되지 않아 분석할 수 없습니다."
-
동의가 확인되면 아래 방법으로
.sodam-re/consent-log.jsonl에 한 줄을 추가한다(파일 없으면 새로 생성, 기존 내용 뒤에 append). JSON을 손으로 만들어 Write하거나 Bash echo/printf로 직접 쓰지 않는다 — 윈도우 경로의 백슬래시가 수동 이스케이프 누락(2026-08-19)과 셸 자체의 이스케이프 처리(2026-08-21, Git Bash가 이중 백슬래시를 다시 벗겨냄)로 두 번 실제로 깨진 전례가 있다:Write도구로 임시 스크립트.sodam-re/_consent_tmp.mjs를 만든다:import fs from 'fs'; const entry = { id: 'con-' + Date.now(), target_scope: String.raw`$ARGUMENTS`, ownership: '<질문1 응답 그대로>', disclaimer_ack: true, agreed_at: new Date().toISOString(), }; fs.appendFileSync('.sodam-re/consent-log.jsonl', JSON.stringify(entry) + '\n');Bash로node .sodam-re/_consent_tmp.mjs실행(파일명만 넘기므로 셸 이스케이프 위험 없음).- 실행 후 스크립트 파일은 삭제한다.
왜 이 방식인가:
String.raw는 백슬래시를 이스케이프 없이 그대로 쓸 수 있게 하고,JSON.stringify()가 나머지 이스케이프를 전담한다 — AI가\를\\로 세어 바꾸는 수작업 자체가 없어진다.Write도구는 셸을 거치지 않으므로 Bash의 이스케이프 문제도 원천 차단된다. (02_DATA_MODEL의 ConsentRecord,session_id는 생략 — SafetyLog와 동일한 fail-safe: 기록 실패해도 분석은 계속 진행)
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.
- 5d ago Changed · +12 lines 4b40f5a9858b
- 10d ago First seen · 84 lines · 25 tokens per session scan A dfb64bcfb0f6
re-start is a command published in the GitHub repository sodam-ai/SoDam-Reverse-Eng (4 stars, last pushed 8d ago), licensed Apache-2.0. It adds 25 tokens to every session and 1,566 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
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.
natural-english
A Korean-to-English writing helper that turns Korean sentences into natural English and briefly explains the wording.
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.