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 christopherlouet/claude-base --skill qa-chromegit clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/christopherlouet/claude-base/qa-chrome)<a href="https://agentmods.dev/skills/christopherlouet/claude-base/qa-chrome"><img src="https://agentmods.dev/badge/skills/christopherlouet/claude-base/qa-chrome.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 | $0.00061 | $0.00598 |
| Opus 5 | $0.00030 | $0.00299 |
| Sonnet 5 | $0.00012 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
qa-chrome 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 3d 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.
What it actually says
Visual Tests and Chrome Debugging (pointer)
DevTools features (network inspection, profiling, accessibility tree, console replay) are canonical at the Chrome team's MCP server:
ChromeDevTools/chrome-devtools-mcp— github.com/ChromeDevTools/chrome-devtools-mcp (Apache-2.0, maintained by the Google Chrome DevTools team). Configure in.mcp.jsonto give Claude Code direct programmatic access during a session.
This skill scopes to the manual-review checklist when using Claude Code's --chrome flag — what to look for, not how the API works.
Prerequisites
- Claude Code launched with
--chrome - "Claude in Chrome" extension v1.0.36+
- Google Chrome open (not Brave/Arc/Firefox; no headless mode; WSL unsupported)
Manual-review checklist
When asked to visually validate a page or flow:
- Page loads with no console error
- Layout correct (no overflow, no overlap, no z-index bug)
- Text readable (contrast meets WCAG AA — see
wcag-audit) - Images loaded (no broken sources, lazy-load completes)
- Links functional (no 404 in network panel)
- Forms submittable (validation triggers on bad input)
- Responsive OK across mobile/tablet/desktop breakpoints — see
qa-design(responsive category) - No network error (no 4xx/5xx unless intentional)
Expected output
Structured report:
- Screenshots/GIFs of issues
- List of console + network errors with source location
- Recommendations sorted by severity
- Overall verdict:
OK/Warnings/Errors
See also
chrome-devtools-mcp(vendor MCP server, programmatic layer) —docs/recipes/recommended-vendor-skills.mdqa-designskill — UI/UX heuristics + responsive/breakpoint testing complementwcag-audit— accessibility gate when contrast/readability issues surface- Audit pilot trace:
specs/marketplace-audit/qa-skills-pilot-2026-05-06.md
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.
- 3d ago First seen · 56 lines · 61 tokens per session scan A a70b1d2a3cff
qa-chrome is a skill published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 598 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
playwright-driver
Use this skill when executing web tests via the canonical playwright npm package (Microsoft, Apache-2.0). Dispatched by skills/test-runner/ to execute web tests against a target, captures token-frugal AX-tree snapshots + screenshots + console output under .orchestrator/metrics/test-runs/ /, and exits with…
peekaboo-driver
Use this skill when driving native-UI AX-tree snapshots and screenshots via steipete/peekaboo (MIT, macOS-only). Dispatched by skills/test-runner/ to capture native-UI AX-tree snapshots + screenshots on macOS 15+ targets, and exits with deterministic JSON output the orchestrator can parse.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
memstack-development-webapp-testing
Use when the user says 'write browser tests', 'test this page', 'playwright test', 'e2e test', 'end to end test', 'browser test', 'test the UI', or needs Playwright-based browser testing for a web application. Do NOT use for unit tests, API tests, or non-browser testing.
qa-testing-playwright
Builds and debugs Playwright E2E suites. Use when authoring browser tests, fixing flakes, or hardening Playwright CI and locator strategy.
qa-persona-testing
Tests apps as an ICP persona through browser automation and reports friction, fixes, and risks. Use when running persona-based, ICP, or synthetic-user testing.