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 ui-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/ui-verify-checks)<a href="https://agentmods.dev/skills/jhlee0409/omni-harness-kit/ui-verify-checks"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/ui-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/ui-verify-checks"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/ui-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 | $0.00114 | $0.01442 |
| Opus 5 | $0.00057 | $0.00721 |
| Sonnet 5 | $0.00023 | $0.00288 |
| Haiku 4.5 | $0.00011 | $0.00144 |
Grade A, and why
ui-verify-checks scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -o /dev/null -w '%{http_code}' <backend base URL> How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI verification — 7 real-browser checks
A UI change is NOT done until it renders correctly in a real browser. The recurring failure modes: broken scroll, off-screen buttons, selection state that does not propagate, render passing while behavior is broken. This skill catches them before work is reported complete.
Setup
- Identify which sub-context changed from
git diff --name-only. - Read that sub-context's
DESIGN.mdfirst. Separate stacks may have separate tones and tokens; verify against the right one. - Identify the changed route/page from the diff.
- Start the dev server if it is not running (
npm run dev/viteon the app's own port). Wait for it to be ready before navigating.
Environment fail-fast rule (CRITICAL — distinguishes "environment" from "UI defect")
The trigger is the server being UNREACHABLE at the TRANSPORT layer: the dev server won't start, or a probe of the backend base URL returns connection-refused / ECONNREFUSED / DNS-fail / timeout — the process is not up, there is NO HTTP response at all.
An HTTP error is NOT environment failure: a 4xx/5xx (even a blanket one) means the server IS up and RESPONDING — a 500 can be a genuine backend bug, and a blanket 401/403 is usually fake-auth / wrong-cred → CANT-VERIFY (see Checks), NOT environment.
Before declaring "environment", PROBE the transport:
curl -sS -o /dev/null -w '%{http_code}' <backend base URL>
- No HTTP code (refused / timeout) = environment fail-fast.
- ANY code (even 500) = server is up, stay on the §Checks verdict (FAILURE / CANT-VERIFY).
On a genuine transport-unreachable signal STOP: report environment problem — server/backend process not running (transport-unreachable), environment must be fixed first in ONE line and end. Do NOT retry endlessly, re-screenshot, or fall into a long static-analysis fallback — one fail-fast verdict, then stop.
A cold next dev / vite compile is NOT "down": browser_wait_for a stable anchor first; only a refused transport AFTER that is environment.
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 · 74 lines · 114 tokens per session scan A 7fac850602b5
ui-verify-checks is a skill published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 1,442 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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…
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
test-implement
Implements React/TypeScript unit, integration, and browser E2E tests with the repository's configured runner, mocks, setup, and browser harness. Use when creating or completing frontend tests and generated test skeletons.
symfony:functional-tests
Write functional tests for Symfony controllers and HTTP endpoints using WebTestCase, getContainer, loginUser, and DAMA rollback.
writing-dev-server-tests
Guides writing HMR/Dev Server tests in test/bake/. Use when creating or modifying dev server, hot reloading, or bundling tests.