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-Harness-Eng --skill sodam-harness-self-checkgit 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/skills/sodam-ai/sodam-harness-eng/sodam-harness-self-check)<a href="https://agentmods.dev/skills/sodam-ai/sodam-harness-eng/sodam-harness-self-check"><img src="https://agentmods.dev/badge/skills/sodam-ai/sodam-harness-eng/sodam-harness-self-check/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-harness-eng/sodam-harness-self-check"><img src="https://agentmods.dev/badge/skills/sodam-ai/sodam-harness-eng/sodam-harness-self-check.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 | $0.00051 | $0.00397 |
| Opus 5 | $0.00026 | $0.00198 |
| Sonnet 5 | $0.00010 | $0.00079 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
sodam-harness-self-check 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 12d 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
자가검증 (SoDamHarness)
당신(AI)은 "다 됐어요"라고 말하기 전에 아래를 지킵니다. (아주 사소한 작업은 건너뛰어도 됩니다 — 위험·중요 작업과 "완료" 선언 때 적용하세요.)
끝내기 전 3단계
- 확인 — 말로만 "됐다" 하지 말고 실제로 점검하세요. 파일이 진짜 생겼나/바뀌었나, 명령이 됐나를 직접 확인(폴더에 파일이 있는지, 내용이 맞는지).
- 증거 — 확인한 것을 쉬운 한국어로 보여주세요. 예) "index.html 파일이 생겼어요. 열어보니 제목과 버튼이 들어 있어요."
- 솔직 — 확인 못 했거나 안 된 부분은 숨기지 말고 말하세요. 예) "이 부분은 직접 확인 못 했어요" · "여기는 안 됐어요".
도구 연결
- 방금 한 일이 궁금하면 →
/sodam-harness:log(활동 타임라인) - 잘못됐으면 →
/sodam-harness:undo(백업에서 골라 복구)
정직 (과장 금지)
- "100% 완벽" · "무조건 작동" 같은 말은 하지 마세요. 확인한 사실과 확인 못 한 부분을 나눠서 말하세요.
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.
- 12d ago First seen · 21 lines · 51 tokens per session scan A a0650f8055b2
sodam-harness-self-check is a skill published in the GitHub repository sodam-ai/SoDam-Harness-Eng (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 397 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
sodam-loop-repair
A Bash safety rule requiring every Bash call to include a timeout calculated from validation settings, with a stated default of 300000 milliseconds. Bash is a command-line shell used to run scripts and commands.
sodam-loop-status
A self-check command for SoDamLoop, a software system with safety components. It checks whether those components are still working normally.
learning-from-experience
Turns incidents, near misses, bad handoffs, review surprises, escaped bugs, and signals from real use into lasting fixes to your safeguards. Use after something went wrong or nearly did and a future safeguard should change. Do not use during a live incident, which comes first, or to blame someone.
reporting-shared-defects
Routes a defect found in a shared or supplied artifact (a shared prompt, skill, dependency, model, eval, or template) to the downstream teams, agents, and releases that depend on it, not just a local fix. Use when a discovered defect affects others who consume the same artifact. Do not use for a defect local to your…
responding-to-incidents
Runs a live incident the stabilize-first way — name a commander, separate facts from hypotheses, prefer reversible actions, communicate on a cadence, and drive corrective actions to closure. Use when production is broken, data is at risk, or an agent action caused harm. Do not use for routine non-incident work, or as…
thumbgate-doctor
Health-check whether ThumbGate is actually wired into this agent — PreToolUse/SessionStart hooks installed, MCP server reachable, lesson store present, statusline, and overall agent-readiness — then report exactly what to fix. Runs the existing npx thumbgate doctor audit and the checkoperationalintegrity MCP tool. Use…