Borrowing it
Nothing to install: this file belongs to junh0328/harness-diagnostics. 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/junh0328/harness-diagnostics/main/AGENTS.mdgit clone --depth 1 https://github.com/junh0328/harness-diagnosticsWrote 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/junh0328/harness-diagnostics/agents-md)<a href="https://agentmods.dev/instructions/junh0328/harness-diagnostics/agents-md"><img src="https://agentmods.dev/badge/instructions/junh0328/harness-diagnostics/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/junh0328/harness-diagnostics/agents-md"><img src="https://agentmods.dev/badge/instructions/junh0328/harness-diagnostics/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 | $0.00664 | $0.00664 |
| Opus 5.5 | $0.00266 | $0.00266 |
| Sonnet 5.5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
harness-diagnostics AGENTS.md 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 2mo 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
GitHub 레포지토리용 AGENTS
이 문서는 harness-diagnostics GitHub 레포지토리를 수정하는 에이전트를 위한 운영 가이드다.
스킬 런타임 지침은 SKILL.md, 사람용 설명은 README.md를 기준으로 본다.
역할
- 이 standalone 레포는
harness-diagnostics의 source of truth다. $HOME/.codex/skills/harness-diagnostics는 배포 대상 복사본이며 직접 수정하지 않는다.- 이 문서는 GitHub 레포지토리 운영용이다. issue, PR, CI, release sync 같은 저장소 작업 규칙을 다룬다.
시작 순서
- 스킬 런타임 계약은 SKILL.md에서 확인한다.
- 로컬 작업 전
.nvmrc기준으로 Node 20을 맞추고bash scripts/install-hooks.sh로 local pre-commit을 설치한다. - 검증과 self 로그 운영 규칙은 references/verification-workflow.md에서 확인한다.
- 릴리즈와 동기화 흐름은 README.md의 설치/동기화 및 버전 관리 섹션을 따른다.
작업 규칙
SKILL.md는 짧고 map 지향적으로 유지하고, 상세 설명은references/,examples/,scripts/로 내린다.- 새 runtime 파일을 추가하면
SKILL.md,README.md,scripts/sync-to-codex.sh를 함께 갱신한다. - 의미 있는 변경 뒤에는 반드시 로컬 검증을 수행하고 logs/self-audit-log.md에
skill-self요약을 남긴다. - GitHub 템플릿과 workflow를 수정하면
.codex복사본에서도 같은 self-audit가 통과하는지 확인한다.
필수 검증
레포 루트에서 아래 명령을 실행한다.
bash scripts/check-node-version.sh
bash scripts/self-audit.sh
bash scripts/maintenance-scan.sh
bash scripts/adversarial-verify.sh
bash scripts/semantic-verify.sh
bash scripts/behavioral-verify.sh
node scripts/calculate-score.js references/score-template.json
릴리즈 동작이나 sync manifest를 수정했으면 아래도 실행한다.
bash scripts/release-sync.sh
릴리즈 절차
- 문서, 스크립트, 템플릿을 함께 갱신한다.
SKILL.mdversion과 CHANGELOG.md를 업데이트한다.- 검증 명령을 실행한다.
- self 점수와 변경 메모를 logs/self-audit-log.md에 기록한다.
- 브랜치에서 커밋하고 PR을 생성한 뒤 체크 통과 후 머지한다.
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.
- 2mo ago First seen · 53 lines · 664 tokens per session scan A 8645840138af
harness-diagnostics AGENTS.md is an instructions file published in the GitHub repository junh0328/harness-diagnostics (11 stars, last pushed 7mo ago), licensed MIT. It adds 664 tokens to every session, about $0.0027 per session on Opus 5.5. 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 2026-08-30.
harness-diagnostics AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| harness-diagnostics AGENTS.mdjunh0328/harness-diagnostics | Instructions file | 11 | 7mo ago | MIT | A | 664 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |