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 spencerpauly/awesome-cursor-skills --skill verifying-in-browsergit clone --depth 1 https://github.com/spencerpauly/awesome-cursor-skillsWrote 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/spencerpauly/awesome-cursor-skills/verifying-in-browser)<a href="https://agentmods.dev/skills/spencerpauly/awesome-cursor-skills/verifying-in-browser"><img src="https://agentmods.dev/badge/skills/spencerpauly/awesome-cursor-skills/verifying-in-browser/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/spencerpauly/awesome-cursor-skills/verifying-in-browser"><img src="https://agentmods.dev/badge/skills/spencerpauly/awesome-cursor-skills/verifying-in-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00049 | $0.00579 |
| Opus 5 | $0.00024 | $0.00290 |
| Sonnet 5 | $0.00010 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
verifying-in-browser 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify in Browser
Use this skill proactively after making code changes to verify the app actually works. Don't just trust that the code is correct — launch it and check.
Steps
-
Start the dev server in the background — check if one is already running by listing terminals. If not:
npm run devSet
block_until_ms: 0to run it in the background. Then poll until you see the "ready" message with the localhost URL. -
Open in the side browser — launch the app beside your code:
Tool: browser_navigate Arguments: { "url": "http://localhost:3000", "position": "side", "take_screenshot_afterwards": true } -
Quick health check — run these three checks:
Console errors:
Tool: browser_console_messagesFlag any errors. Warnings about deprecations can be noted but aren't blockers.
Network failures:
Tool: browser_network_requestsFlag any 4xx/5xx responses, failed fetches, or CORS errors.
Visual check: Review the screenshot. Does the page render? Is the layout correct? Are there any blank screens or loading spinners that never resolve?
-
Navigate to the changed page — if your changes are on a specific route, navigate there and repeat the checks.
-
Test interactions — if you changed a form, button, or interactive element:
- Take a
browser_snapshotto get element refs - Click, fill, or hover on the changed elements
- Take another screenshot to verify the result
- Take a
-
Report the verdict — tell the user:
- "Verified in browser — page renders correctly, no console errors, all network requests healthy."
- Or: "Found issues: [list of problems]"
When to Use This
- After changing any React component, CSS, or layout code
- After modifying API routes or data fetching
- After updating environment variables or configuration
- After installing or removing dependencies
- Before committing — as a final sanity check
Notes
- Use
position: "side"to see code and browser at the same time. - If the dev server is already running, skip step 1 and go straight to navigating.
- For SSR apps, check both the initial server-rendered HTML and the client-hydrated state.
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 · 68 lines · 49 tokens per session scan A 8b92f36f99eb
verifying-in-browser is a skill published in the GitHub repository spencerpauly/awesome-cursor-skills (770 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 49 tokens to every session and 579 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
chrome-performance-optimizer
Autonomous multi-agent performance optimization loop for Chromium and V8. Supports profile-seeded mode (analyzing Speedometer 3 / JetStream profiles via pprof or Sagacity MCP) and pattern-driven discovery mode (fan-out exploration of Blink and V8 macro-patterns grounded in historical wins and past rejected CLs).…
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.