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 studioKjm/ai-harness-template --skill verifygit clone --depth 1 https://github.com/studioKjm/ai-harness-templateWrote 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/studiokjm/ai-harness-template/verify)<a href="https://agentmods.dev/skills/studiokjm/ai-harness-template/verify"><img src="https://agentmods.dev/badge/skills/studiokjm/ai-harness-template/verify/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/studiokjm/ai-harness-template/verify"><img src="https://agentmods.dev/badge/skills/studiokjm/ai-harness-template/verify.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 | $0.00079 | $0.00369 |
| Opus 5.5 | $0.00032 | $0.00148 |
| Sonnet 5.5 | $0.00016 | $0.00074 |
| Haiku 4.5 | $0.00008 | $0.00037 |
Grade A, and why
verify 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 14d 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
로컬 검증 (증거 기반)
완료를 선언하기 전에 증거(명령 출력, 스크린샷)를 확보한다. 타입체크나 lint 통과만으로는 동작 검증이 아니다.
- 정적 검사: 변경 파일에 대한 lint와 타입체크 (프로젝트의
CLAUDE.md명령 참고). 기존 오류(baseline)와 이번 변경의 오류를 구분한다. - 환경: 로컬 DB/서비스가 떠 있는지 확인하고, 앱이 로컬 환경변수를 가리키는지 확인한다. 원격 운영 값으로 앱을 띄우지 않는다.
- 서버를 백그라운드로 실행하고 준비될 때까지 기다린다.
- 브라우저(claude-in-chrome 등)로 접속해 시드 계정으로 로그인하고, 변경한 기능의 인수 조건을 하나씩 확인한다.
- 역할이 여러 개 관련되면 각 역할로 확인하고, 권한이 없는 역할의 접근이 차단되는지도 본다.
- 브라우저 콘솔과 서버 로그에 새 오류가 없는지 확인한다.
- 서버 프로세스와 열었던 탭을 정리한다.
- 결과를 짧게 보고한다. 확인하지 못한 것은 확인하지 못했다고 적는다.
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.
- 14d ago First seen · 18 lines · 79 tokens per session scan A 307e99cb3087
verify is a skill published in the GitHub repository studioKjm/ai-harness-template (45 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 369 once invoked, about $0.0003 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 2026-10-02.
Other skills, from other repositories
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Browser Agent QA Testing
Teach agents to use AI browser agents for exploratory and smoke QA with step budgets, evidence-based assertions, guardrails, and Playwright conversion.
mstar-e2e
Runs separately requested E2E, real-browser, device, or installed-deployment verification and produces scoped evidence. Loads only for an explicit user request or amazing-e2e-check entry; never from routine QA, UI changes, missing screenshots, or review recommendations.
browse
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. 100ms per command. Use when you need to test a…
gstack
Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or…
browser-proof
Browser-visible verification — route smoke, screenshots, console errors. Receipt required.