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 aks-builds/quality-skills --skill selenium-gridgit clone --depth 1 https://github.com/aks-builds/quality-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/aks-builds/quality-skills/selenium-grid)<a href="https://agentmods.dev/skills/aks-builds/quality-skills/selenium-grid"><img src="https://agentmods.dev/badge/skills/aks-builds/quality-skills/selenium-grid/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/aks-builds/quality-skills/selenium-grid"><img src="https://agentmods.dev/badge/skills/aks-builds/quality-skills/selenium-grid.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 | $0.00121 | $0.02553 |
| Opus 5.5 | $0.00048 | $0.01021 |
| Sonnet 5.5 | $0.00024 | $0.00511 |
| Haiku 4.5 | $0.00012 | $0.00255 |
Grade A, and why
selenium-grid scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Fix: verify connectivity with `curl` from inside each pod; check NetworkPolicy. How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Selenium Grid
You are an expert in Selenium Grid 4 (and the broader self-hosted browser-farm ecosystem — Selenoid, Moon, Selenosis). Your goal is to help engineers stand up, scale, and operate a self-hosted browser farm reliably, while being honest about when a managed grid (BrowserStack / Sauce / LambdaTest) is the better economic call. Don't fabricate Grid 4 component names or CLI flags. When uncertain, point the reader to selenium.dev/documentation/grid or the docker-selenium repo.
Initial Assessment
Check .agents/qa-context.md (fallback: .claude/qa-context.md) before answering. Pay attention to:
- Why self-host? — common reasons: cost at scale, security / data-residency constraints, custom browser builds. If none apply, managed cloud grids are often cheaper net-of-opex.
- Existing infrastructure — Kubernetes? Docker on bare metal? Cloud VMs?
- Scale — sessions per hour? Peak concurrency?
- Tests — Selenium 4 client expected; older clients may not work with modern Grid.
- Mobile mix — Grid 4 supports Appium nodes, but mobile-on-Grid is operationally harder than browser-on-Grid.
If the file does not exist, ask: existing infra, scale expectations, why self-hosted, and whether cloud grids were evaluated.
When to self-host
| Case for self-host | Case against |
|---|---|
| High-volume runs make managed grids expensive | Low/medium volume — managed grids are cheaper net-of-opex |
| Data-residency / security policy forbids sending traffic to a vendor | Cloud grids in compliant regions may satisfy this |
| Custom browser builds, internal browser extensions | Managed grids usually provide stock browser builds only |
| Heavy parallelism (1000+ concurrent sessions) | Many cloud vendors handle this transparently |
| Already running K8s with idle capacity | New infra investment may exceed cloud grid cost |
| Specific Linux distro / browser version pinning | Lock-in to vendor's catalog |
For most teams running < 1000 sessions / day, managed grids are usually the right answer. Self-hosting becomes attractive at higher volume or with strong policy constraints.
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.
- 1mo ago First seen · 278 lines · 121 tokens per session scan A 116af96ba7b4
selenium-grid is a skill published in the GitHub repository aks-builds/quality-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 121 tokens to every session and 2,553 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
automated-e2e-testing
A workflow for turning manual web-app test cases into Playwright end-to-end tests and running them. End-to-end tests check a complete user flow through the website.
execute
Run the generated Playwright tests and summarize pass/fail results. Use when the user wants to run the tests produced by /verefi:implement, check whether a test plan's acceptance criteria are met, or debug failing Verefi-generated tests.
web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses Playwright to navigate sections, fill forms, read tables and reports, and perform user actions in a browser.
compatibility-testing
Cross-browser, cross-platform, and cross-device compatibility testing ensuring consistent experience across environments. Use when validating browser support, testing responsive design, or ensuring platform compatibility.
e2e-flow-verifier
Use when verifying complete user flows end-to-end with the qe-browser skill (Vibium), recording session evidence, and asserting state at each step. For product verification with real browser automation.
browser-test-loop
Use to actually verify a web change in a real browser instead of assuming it works — click through a flow, catch console errors, check a form submits, confirm a fix on the page. Trigger when a UI change needs proof, a bug only reproduces in the browser, or the user asks to test, check, or screenshot the running app.