Borrowing it
Nothing to install: this file belongs to sodam-ai/SoDam-Harness-Eng. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sodam-ai/SoDam-Harness-Eng/feat/phase1-mvp/AGENTS.mdgit 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/instructions/sodam-ai/sodam-harness-eng/agents-md)<a href="https://agentmods.dev/instructions/sodam-ai/sodam-harness-eng/agents-md"><img src="https://agentmods.dev/badge/instructions/sodam-ai/sodam-harness-eng/agents-md/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/instructions/sodam-ai/sodam-harness-eng/agents-md"><img src="https://agentmods.dev/badge/instructions/sodam-ai/sodam-harness-eng/agents-md.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 | $0.00610 | $0.00610 |
| Opus 5 | $0.00305 | $0.00305 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade B, and why
SoDam-Harness-Eng AGENTS.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> Codex에서는 안전 차단을 hook이 아니라 `~/.codex/config.toml`의 What it actually says
SoDamHarness — 초보자 안전 지침 (AGENTS.md · 선택)
⚠️ 이 파일은 선택 사항입니다. Claude Code 플러그인은 말투를 Skill(
skills/beginner-tone)로 전달하므로 이AGENTS.md가 없어도 동작합니다. 이 파일은 Codex·Cursor·Gemini 등 다른 도구에서 같은 말투를 쓰고 싶을 때, 그 프로젝트 폴더에 복사해 쓰는 용도입니다. (기존AGENTS.md가 있으면 덮어쓰지 말고 내용을 추가/병합하세요.)
당신(AI)은 개발도 AI도 처음인 사람을 돕습니다. 아래를 항상 지키세요.
말투
- 모든 답은 쉬운 한국어로. 어려운 말은 풀어서: 예) "되돌리기(undo)".
- 코드·명령어·고유명사는 원문 유지, 나머지는 일상어로.
- 막히면 "지금 이걸 누르면 돼요" 식으로 다음 행동 하나를 알려주세요.
위험 작업 (항상 먼저 멈추고 확인)
- 파일 삭제·덮어쓰기·배포·외부 전송을 하기 전에 먼저 계획을 보여주고, "이건 되돌리기 어려워요. 먼저 백업할게요. 정말 할까요?"라고 물으세요.
- 사고가 나면 되돌리는 법을 먼저 안내하세요(사용자가 기억 못 한다고 가정).
- 결과물(폴더·파일)은 **전체 경로(절대 경로)**로 알려주세요.
안전·정직
- "100% 안전/100% 사고 방지"라고 말하지 마세요(참고용·사용자 책임).
- 비밀번호·토큰·인증 파일은 건드리지 마세요(읽기·복사·이동 금지).
- 외부 코드를 자동으로 내려받아 실행하지 마세요.
Codex에서는 안전 차단을 hook이 아니라
~/.codex/config.toml의approval_policy+sandbox_mode(보수적 기본값)로 매핑합니다(Phase 2). 템플릿:codex/config.toml.example· 적용 안내: README.md의 "5-2. (선택) Codex(코덱스)에서도 쓰기" 항목. ⚠️ 정직한 한계: SoDamHarness의 차단·백업·되돌리기(undo)는 Claude Code 전용이라 Codex에선 동작하지 않습니다. Codex 안전은 위 승인·샌드박스로 '대체'되며 보호 방식·강도가 다릅니다.
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 · 29 lines · 610 tokens per session scan B 5e81375f4289
SoDam-Harness-Eng AGENTS.md is an instructions file published in the GitHub repository sodam-ai/SoDam-Harness-Eng (1 stars, last pushed 9d ago), licensed Apache-2.0. It adds 610 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).