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 damianvtran/local-operator --skill browser-qagit clone --depth 1 https://github.com/damianvtran/local-operatorWrote 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/damianvtran/local-operator/browser-qa)<a href="https://agentmods.dev/skills/damianvtran/local-operator/browser-qa"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/browser-qa/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/damianvtran/local-operator/browser-qa"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/browser-qa.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 | $0.00045 | $0.00635 |
| Opus 5.5 | $0.00018 | $0.00254 |
| Sonnet 5.5 | $0.00009 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
browser-qa 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 5d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser QA
Exercise the web surface with the harness browser tool: reconnaissance, then action, then capture the resulting state. Concrete flows: references/recipes.md.
Recon before acting
- Open the target and wait for READY, not just present: await the element you are about to use, never click on a fixed sleep.
- Read the page first: structure, headings, controls, current URL. Build the selector plan from what is actually there (snapshot refs, roles, labels), not from guesses.
- Note the auth state and anything that will swallow your first click (cookie banners, interstitials, modals).
Act, then capture the state
- After every action capture BOTH: the action performed and the resulting state (URL, the target element's text or attributes, visible feedback). "Clicked button" and "order confirmed, ref #1234 shown" are different evidence.
- Verify the intended effect, not just the absence of an error: row created, redirect happened, message shown, count changed.
- Re-read the page after anything that navigates or re-renders; stale element refs are the top cause of flaky interaction.
- Check side effects you can reach: the list the form wrote to, the request that was sent, the message queued.
Console, network, screenshots
- After the flow, read the console logs. Errors and failed requests are defects until explained; correlate UI symptoms with the console entry that caused them.
- Screenshot the settled state (after animations). When a flow has loading and populated phases, both are evidence; keep each.
- Screenshot at a width that shows the defect, narrow for reflow bugs, and keep the frame next to the claim it supports.
Rig hygiene
- Reuse ONE browser instance across a run's cases. Never launch a fresh browser per case, and never install or script a browser engine: the harness tool drives the user's real browser with their logins intact.
- Headless stays headless: no windows raised, no focus stolen, no visible tabs spawned per case.
- Scripted rigs: tear down by process group, reaped by exact pid. Close the tab you opened when the run ends.
What ships with it
1 file 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.
- 5d ago First seen · 46 lines · 45 tokens per session scan A 5ab24a3f8024
browser-qa is a skill published in the GitHub repository damianvtran/local-operator (218 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 635 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
agent-browser
Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.
checking-a-page
Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it. Use after creating or editing an HTML page, or the JavaScript or CSS that a page loads.
web-system-tests
The web realization of the system-tests contract — browser-driven system tests with Playwright against a running frontend. Owns the project layout (tests/), the Playwright configuration (baseURL plus webServer, cross-engine projects), the role- and label-based selector policy, code coverage as an opt-in second run…