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 pnakhat/qa-ai-repo --skill ui-test-auditorgit clone --depth 1 https://github.com/pnakhat/qa-ai-repoWrote 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/pnakhat/qa-ai-repo/ui-test-auditor)<a href="https://agentmods.dev/skills/pnakhat/qa-ai-repo/ui-test-auditor"><img src="https://agentmods.dev/badge/skills/pnakhat/qa-ai-repo/ui-test-auditor/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/pnakhat/qa-ai-repo/ui-test-auditor"><img src="https://agentmods.dev/badge/skills/pnakhat/qa-ai-repo/ui-test-auditor.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 | $0.00150 | $0.01801 |
| Opus 5 | $0.00075 | $0.00901 |
| Sonnet 5 | $0.00030 | $0.00360 |
| Haiku 4.5 | $0.00015 | $0.00180 |
Grade A, and why
ui-test-auditor 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Test Overuse Auditor
Browser tests are the slowest, flakiest, most expensive tests to run and
maintain. Teams overuse them — verifying business rules, validation, permissions,
and data variations through the UI when a fast API or unit test would prove the
same thing. This skill audits the suite and reclassifies each test:
keep-as-UI, demote-to-API, or demote-to-unit. See
detection-signals.md for framework/language markers and the exact rubric, and
reference.md for concrete before/after conversions and copy-pasteable ripgrep
inventory commands.
How to run the audit
- Locate the UI tests regardless of framework/language. Detect Playwright,
WebdriverIO, and Selenium/WebDriver by their imports/APIs (see
detection-signals.md). Count files and test cases; note the framework+language. - Establish the shape. Compare UI test count against API/unit test counts. A healthy suite has a handful of UI journeys, not hundreds. Flag inversion.
- Classify each UI test by what it actually verifies (read the assertions,
not the title):
- Keep-as-UI — the behavior only manifests in the browser: rendering, client-side interaction, navigation/routing, form UX, visual, accessibility, or a genuine critical end-to-end journey.
- Demote-to-API — business rules, validation messages, permission/authz, error codes, pagination/filtering/sorting, calculations, data transformations — anything asserted on data/state, reachable via an HTTP call.
- Demote-to-unit — pure logic with no I/O.
- Find the repetition. The biggest win: N UI tests that differ only by input data (each retyping a form to check a different validation/branch). Collapse them into one parameterized API test plus one UI happy-path smoke.
- Flag UI-driven setup. Logging in, seeding data, or navigating through the UI just to reach a state = move to programmatic/API setup or fixtures; it's not what the test verifies.
- Report with
audit-report-template.md: inventory, overuse findings ranked by cost saved, per-test recommendation with reasoning, the target counts, and a migration plan.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 106 lines · 150 tokens per session scan A 39bcd4866a51
ui-test-auditor is a skill published in the GitHub repository pnakhat/qa-ai-repo (2 stars, last pushed 2mo ago), licensed MIT. It adds 150 tokens to every session and 1,801 once invoked, about $0.0007 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
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
test-loop
Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…