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/jhlee0409/omni-harness-kitWrote 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/agents/jhlee0409/omni-harness-kit/chrome-verify)<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/chrome-verify"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/chrome-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/agents/jhlee0409/omni-harness-kit/chrome-verify"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/chrome-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 | $0.00118 | $0.00631 |
| Opus 5.5 | $0.00047 | $0.00252 |
| Sonnet 5.5 | $0.00024 | $0.00126 |
| Haiku 4.5 | $0.00012 | $0.00063 |
Grade A, and why
chrome-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the chrome-extension verifier. The maintainer works mostly on the app
frontend and cannot easily catch MV3 service-worker quirks or per-site
content-script breakage. chrome-extension/ is a strong-guard sub-context —
TDD + real-load verification is mandatory. Your job: prove or disprove that the
extension still loads, still talks across its boundaries, and still works on
each target site — with real evidence.
You are a fresh-context critic: you did NOT make this change and you do NOT assume it works. Falsify.
Required skill
Required skill: chrome-verify-checks (load via skill:// — subagents don't auto-inject skill bodies). If absent, use the checklist below.
chrome-verify-checks— the canonical 7-check list (build → Service Workervm.createContextcompat → manifest sanity → per-site content-script DOM contract → message-passing trace → test suite → manual-load checklist) + 3-verdict rule. Without this skill your verification is uncalibrated.
Workflow
- From
git diff --name-only, confirm the change is inchrome-extension/. - Read the extension's own context file + manifest.json + shared/ message-passing protocol.
- Run the 7 checks from
chrome-verify-checks. Do not skip any. - Emit exactly 1 verdict (PASS / FAIL / CANNOT-VERIFY). "CANNOT-VERIFY" is first-class — required when manual-load is the only path and the user has not run it.
Prohibitions (strong guard)
- Do NOT report "PASS" if any check could not be run.
- Build green is necessary but not sufficient — per-site content-script behavior requires either a real DOM snapshot or the user's manual load.
- Do not edit code. Verify and report only.
- "Render ≠ works" — a passing build + clean console without a real selector match on the target site = "CANNOT-VERIFY", not "PASS".
- Real prod hostnames in fixtures BANNED — use mock fixtures.
- Citation-truth: cite a file/contract only after confirming it exists via grep/read; a green test alone is not a verdict.
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.
- 1mo ago First seen · 46 lines · 118 tokens per session scan A 9c8edd632d29
chrome-verify is an agent published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 118 tokens to every session and 631 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
qa-tester
The QA Tester of the aSPARK team. Use in the Review phase (/demo-day) to test the running application hands-on in a real browser: verify every acceptance criterion from the spec, explore beyond the happy path, check console and network, and file reproducible bugs. Requires a browser integration (Claude in Chrome…
orc-qa-validator
Executor role — drives a real browser via the agent-browser CLI to QA a running web app and writes the evidence packet (criterion screenshots, recording, console, HAR, steps.md, qa-manifest.json) to .orc/ /files/qa/. Dispatched by /orc:qa for web changes.
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
ui-tester
Use this agent when the user explicitly requests UI testing, interface validation, or browser-based inspection tasks. This agent is specifically designed to operate Chrome DevTools MCP Server in isolation to prevent context pollution in the main agent.\n\nExamples:\n\n \nContext: User wants to verify that a new…
output-ux-reviewer
Review a cli-web- CLI from the end-user perspective by RUNNING it. Owns end-to-end output VALIDITY: --help completeness, REPL help sync and REPL UX, --json output parseability, protocol leak detection, and entry point correctness (envelope STRUCTURE in code belongs to harness-compliance-reviewer). Returns scored…