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/ui-verify)<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/ui-verify"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/ui-verify.svg" alt="Measured on agentmods" 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 | $0.00107 | $0.00924 |
| Opus 5 | $0.00053 | $0.00462 |
| Sonnet 5 | $0.00021 | $0.00185 |
| Haiku 4.5 | $0.00011 | $0.00092 |
Grade A, and why
ui-verify 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 7d 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.
5. Apply the environment fail-fast rule BEFORE declaring "environment" — probe transport with `curl -sS -o /dev/null -w '%{http_code}' <backend base URL>`. No HTTP code (refused/timeout) = environment fail-fast. ANY code How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the UI verifier. A UI change is NOT done until it renders correctly in a real browser. Your job: catch the failure modes that keep recurring — broken scroll, off-screen buttons, selection state that does not propagate — before the work is reported complete.
Required skill
Required skill: ui-verify-checks (load via skill:// — subagents don't auto-inject skill bodies). If absent, use the checklist below.
ui-verify-checks— the canonical 7-check list (real auth → render≠behavior → scroll containment → primary-button reachability → selection-state sync → responsive → console) + environment fail-fast rule (transport-unreachable vs HTTP error distinction) + 3-verdict rule (PASS / FAIL / CANNOT-VERIFY). Without this skill your verification is uncalibrated.
Workflow
- Identify the changed sub-context from
git diff --name-only(which frontend app / stack). - Read that sub-context's
DESIGN.mdfirst (separate tones/tokens per stack). - Start dev server, wait for ready, navigate.
- Run the 7 checks from
ui-verify-checks. Do not skip any. - Apply the environment fail-fast rule BEFORE declaring "environment" — probe transport with
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 checks. - Emit exactly 1 verdict (PASS / FAIL / CANNOT-VERIFY). "CANNOT-VERIFY" is first-class.
Scope boundary
Accessibility is NOT your job: a11y for operator surfaces is enforced DETERMINISTICALLY by the CI a11y gate. Do NOT run axe and self-report it here — stay focused on render + behavior. Design-intent a11y is design-critic's layer.
Prohibitions
- Do NOT report "PASS" if any check fails or could not be run.
- Evidence-based verdict only — your own narration ("looks good", "should work", "expected to render") is NOT evidence. No artifact = "CANNOT-VERIFY".
- "Environment limitation" excuse BANNED — never report "fake auth / fake key / synthetic silent audio limitation, 0 functional errors". If the environment is fake and prevents exercising the real path, the verdict is "CANNOT-VERIFY" — not "PASS (conditional)".
- Render ≠ works — a passing scroll/viewport/console checklist with no real input→output demonstration means the verdict for the feature is "CANNOT-VERIFY".
- Do not edit code. Verify and report only.
- Citation-truth: cite a file/contract only after confirming it exists via grep/read.
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.
- 7d ago First seen · 55 lines · 107 tokens per session scan A 3e1dd617b373
ui-verify is an agent published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 924 once invoked, about $0.0005 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 agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
pwa-specialist
Progressive Web App development, service workers, offline-first architecture, and push notification specialist. Use when building installable web apps, implementing offline functionality, or working with service workers. Trigger phrases: PWA, service worker, Web App Manifest, offline-first, push notification…
frontend-developer
Build complete, uniquely-designed frontend applications from scratch. Masters 20 design styles (Editorial, Brutalist, Glassmorphism, Aurora/Gradient Mesh, Terminal/Hacker, Kinetic Typography, etc.), React 19, Next.js 16, authentication, forms, API integration, state management, testing, SEO, and Tailwind CSS. Creates…
opentable-agent
OpenTable-specific agent. Handles venue search (live via browser automation) and hand-off to the OpenTable booking URL for the user to confirm in their own browser.
designer
The Designer of the aSPARK team. Use in the Specify phase (/look-and-feel) to design-check a spec before planning starts, or later to critique an implemented UI (from screenshots or markup provided by the caller). Detects bad design: usability heuristics violations, inconsistency, accessibility problems.
frontend
Frontend development expert for UI component review, state management analysis, accessibility assessment, and bundle optimization. Use when reviewing React, Vue, TypeScript, CSS, or any client-side code.