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-Harness-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-harness-eng/fix)<a href="https://agentmods.dev/commands/sodam-ai/sodam-harness-eng/fix"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-harness-eng/fix/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-harness-eng/fix"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-harness-eng/fix.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 | $0.00542 |
| Opus 5 | $0.00013 | $0.00271 |
| Sonnet 5 | $0.00005 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
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 11d 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
사용자가 막혔습니다. 쉬운 한국어로, 아래 흔한 문제를 증상 → 왜 → 지금 할 것 순서로 안내하세요. 먼저 사용자에게 "어떤 증상인가요?"를 묻고, 해당하는 항목을 골라 설명합니다.
- 안전벨트가 안 멈춰요 (위험 작업인데 그냥 진행됨)
- 왜: 플러그인이 꺼져 있거나, 우리가 아직 모르는 위험 패턴일 수 있어요(모든 경우를 막지는 못함).
- 지금 할 것: Claude Code를 껐다 켜기 →
/sodam-harness:status로 동작 확인. 그래도면 그 명령을 알려주세요(패턴 보강).
- 너무 자주 물어봐요
- 왜: 안전을 위해 위험해 보이는 작업마다 확인해요.
- 지금 할 것:
/sodam-harness:wizard로 확인 빈도를 조정할 수 있어요(치명적 작업 차단은 항상 그대로예요).
- Node.js가 없대요
- 왜: 안전 훅이 Node.js로 동작해요.
- 지금 할 것: https://nodejs.org 에서 LTS 설치 → Claude Code 재시작.
- 실행 차단 경고가 떠요 (Windows SmartScreen / Mac Gatekeeper)
- 왜: 처음 보는 프로그램이라 OS가 한 번 묻는 거예요.
- 지금 할 것: 공식 경로로 받은 게 맞다면 "추가 정보 → 실행 허용". 출처가 의심되면 멈추세요.
- 되돌리고 싶어요
- 지금 할 것:
/sodam-harness:undo— 백업 목록을 보여주고, 방금 잃은 것을 골라 복구해요(엉뚱한 걸 되돌리지 않도록).
- 지금 할 것:
- 백업 폴더 권한/용량 오류
- 왜: 디스크가 꽉 찼거나 폴더 권한 문제.
- 지금 할 것: 공간 확보 후 다시 시도. 백업을 못 뜨면 안전을 위해 위험 작업은 자동으로 멈춰요.
정직하게: "100% 안전"이라고 말하지 말고, 막히면 사용자 파일은 백업으로 지켜진다는 점을 안내하세요.
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.
- 11d ago First seen · 26 lines · 25 tokens per session scan A 9dc9a191f5b7
fix is a command published in the GitHub repository sodam-ai/SoDam-Harness-Eng (1 stars, last pushed 9d ago), licensed Apache-2.0. It adds 25 tokens to every session and 542 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
repair
A repair-and-check loop for Phase 1a work. It runs only after sodam-loop-start has enabled the loop.
audit
Alias for hallucination-detector hallucination-audit command.
debug
Systematic debugging: root cause before any fix, one hypothesis at a time, and a three-strikes rule that questions the architecture instead of stacking patches.
ng-incident
Portable command prompt generated from skills/responding-to-incidents/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
debug
Systematic debugging with hypotheses and evidence gathering.
debug
Structured debugging with parallel investigation agents.