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 jhlee0409/omni-harness-kit --skill chrome-verify-checksgit 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/skills/jhlee0409/omni-harness-kit/chrome-verify-checks)<a href="https://agentmods.dev/skills/jhlee0409/omni-harness-kit/chrome-verify-checks"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/chrome-verify-checks/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/jhlee0409/omni-harness-kit/chrome-verify-checks"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/chrome-verify-checks.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 | $0.00126 | $0.01206 |
| Opus 5 | $0.00063 | $0.00603 |
| Sonnet 5 | $0.00025 | $0.00241 |
| Haiku 4.5 | $0.00013 | $0.00121 |
Grade A, and why
chrome-verify-checks 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 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.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome extension verification — 7 checks + manual-load checklist
chrome-extension/ is a strong-guard sub-context — a frontend maintainer cannot easily catch MV3 service-worker quirks or per-site content-script breakage. This skill is the canonical verification: 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 when you load this: you did NOT make the change and you do NOT assume it works. Falsify.
Setup
- From
git diff --name-only, confirm the change is inchrome-extension/. - Read the sub-context's own guide (TDD entry) and the manifest
chrome-extension/manifest.jsonfor the current permissions / matches / background entry. - Read
chrome-extension/shared/for the message-passing protocol shape.
The 7 checks (run every one — do not skip)
-
Build the extension —
cd chrome-extension && npm run build:dev. Capture build output. Any error / warning = finding. -
Service Worker compat (
vm.createContext) — there is no dedicated sw-compat script in this repo. Inspect the SW entry fromchrome-extension/manifest.jsonbackground.service_worker, then grep the entry file + its transitive imports for DOM-tied refs (window.,document.,XMLHttpRequest,localStorage) and for modules known to break under MV3 SW (axios with default adapter, anynode:*import, anything pulling injsdom). Any DOM-tied ref in the SW transitive closure = blocking finding. AReferenceError: window is not definedat SW boot (visible fromchrome://extensionson manual load) is the runtime symptom. -
Manifest sanity — verify
manifest_version: 3,background.service_workerpath resolves to a real built file indist/, everyhost_permissionsentry is actually used by code (grep), everymatchesURL pattern resolves to an existing content-script file. -
Per-site content-script DOM contract — for each target site the extension supports, grep the selector strings the content script depends on. If a selector is missing in the live DOM, the script silently no-ops on that site. List each selector + the file:line that owns it + the last-verified date if recorded. If a selector cannot be verified, flag it as CANT-VERIFY — manual browser load required by the maintainer.
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 · 54 lines · 126 tokens per session scan A 14ad0add2fe8
chrome-verify-checks is a skill published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 1,206 once invoked, about $0.0006 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
symfony:e2e-panther-playwright
Write end-to-end tests with Symfony Panther 2.4 for browser automation or Playwright for complex scenarios.
playwright-expert
Use when writing or fixing E2E tests in a Playwright project - playwright.config.ts, .spec.ts files under tests/ or e2e/, @playwright/test imports - or right after implementing a frontend/backend change that needs an end-to-end proof. Writes and extends TypeScript E2E suites as the QA gate for feature and bug-fix…
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
vc:web-testing
Web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.
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.
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.