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 jjanczur/tyran --skill browser-checkgit clone --depth 1 https://github.com/jjanczur/tyranWrote 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/jjanczur/tyran/browser-check)<a href="https://agentmods.dev/skills/jjanczur/tyran/browser-check"><img src="https://agentmods.dev/badge/skills/jjanczur/tyran/browser-check.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 21 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 22 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00058 | $0.01524 |
| Opus 5 | $0.00029 | $0.00762 |
| Sonnet 5 | $0.00012 | $0.00305 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
browser-check 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 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.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser check — proving a UI works, in numbers
Three places in this plugin order a browser pass — the conductor's quality gates, the reviewer, the implementer — and
fidelity-gateasks for computed styles on top. None of them said how. This is the how, and it exists so that "I checked it in the browser" stops being a sentence and starts being a counter someone else can re-run.
A browser pass is a measurement. It returns numbers: pages visited, links
resolved, console errors, failed responses. Looks fine, renders correctly
and no obvious issues are REJECTED by the evidence contract exactly like a
test report with no output, and for the same reason — nothing in them can be
wrong.
Before you promise a run
- The browser exists.
npx playwright --version, and install only chromium (npx playwright install chromium) — a full browser install is several GB for two extra engines nobody asked for. - The server is up and SERVING WHAT YOU THINK. Fetch one known URL and check the status before automating anything. A dev server that is still compiling, or is serving a stale build on a port you forgot to kill, produces a page of failures that have nothing to do with your change.
- Build first when the target is a static site. Testing the dev server and shipping the build tests two different programs.
Waits are deterministic — never a sleep
Wait for a condition: a response, a selector, a network-idle state, a font
ready promise. waitForTimeout is a guess that is simultaneously too long on
your machine and too short in CI, and the failures it produces are
indistinguishable from real ones. The only defensible fixed wait is settling an
animation you cannot observe, and it says so in a comment.
Warm the routes before a batch run. The first request to a route compiles it; a cold compile times out and reads as a defect in the page. Hitting every route once before measuring costs one pass and removes a whole class of false finding.
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 · 131 lines · 58 tokens per session scan A 02fb8327a0b4
browser-check is a skill published in the GitHub repository jjanczur/tyran (86 stars, last pushed 4d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,524 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 2026-08-30.
Other skills, from other repositories
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
chrome-automation
A browser-automation toolkit for controlling Chrome to visit pages, interact with forms, collect data, run tests, and create screenshots or PDFs.
qa
QA testing skill with real browser automation. Use when asked to "test this site", "QA this page", "check for visual bugs", "verify the deploy", or when Hydra needs browser validation for UI changes. Requires the browse binary.
write-e2e
Generate Playwright E2E tests from codebase analysis. Discovers routes, scores user flows by criticality, writes .spec.ts files that assert causality, and reports what was actually proven: GENERATED, STATICCHECKED, VERIFIEDLOCAL or VALIDATEDLIVE. Modes: --scope , --flow , --output , --base-url , --max-flows N, --live…
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
browser-qa
Use to exercise the running app in a real browser — after UI changes, before ship, or when the user asks to QA the site, smoke-test a branch, or check "does it actually work". Drives affected routes headlessly via Playwright, captures console errors, failed requests, and screenshots, and produces a report with a…