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 Autodesk/claude-browser-test-skills --skill authorgit clone --depth 1 https://github.com/Autodesk/claude-browser-test-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/autodesk/claude-browser-test-skills/author)<a href="https://agentmods.dev/skills/autodesk/claude-browser-test-skills/author"><img src="https://agentmods.dev/badge/skills/autodesk/claude-browser-test-skills/author/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/autodesk/claude-browser-test-skills/author"><img src="https://agentmods.dev/badge/skills/autodesk/claude-browser-test-skills/author.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 | $0.00032 | $0.04142 |
| Opus 5 | $0.00016 | $0.02071 |
| Sonnet 5 | $0.00006 | $0.00828 |
| Haiku 4.5 | $0.00003 | $0.00414 |
Grade A, and why
author 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 8d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Test Author
Overview
Transforms a vague user description (e.g., "test the purchase flow") into a structured, precise E2E test case by performing an exploratory browser run, then documenting each step with selectors, wait patterns, and verification points.
Core principle: Run first, document second. You cannot write a reliable test from reading code alone - you must observe the actual browser behavior.
When to Use
- User describes a feature to test but doesn't provide precise steps
- A new feature needs its first E2E test
- User says "write a test for..." or "create a test case for..."
Do NOT use when:
- A structured test case already exists (use
browser-test:runnerinstead) - An existing test is flaky and needs stabilization (use
browser-test:refinerinstead)
Prerequisites
- The Playwright MCP server must be available (configured in
.mcp.json) - Dev server must be running (or
E2E_BASE_URLset to a reachable environment) - Read
tests/e2e/conventions.mdand the relevant area conventions before starting - When invoked with a Jira XRay key (e.g.
/author PROJ-247135), the Atlassian Jira MCP server must be available to fetch test steps and acceptance criteria
Process
digraph author_flow {
rankdir=TB;
"Read conventions" -> "Classify area";
"Classify area" -> "Read area conventions";
"Read area conventions" -> "Exploratory browser run";
"Exploratory browser run" -> "Confirm scenario scope";
"Confirm scenario scope" -> "Classify steps into hooks";
"Classify steps into hooks" -> "Document steps";
"Document steps" -> "Write test case file(s)";
"Write test case file(s)" -> "Hand off to browser-test:refiner";
}
Hook-aware authoring : Every test case the author produces MUST separate observations into three named markdown sections — ## Before Hook, ## Test Steps, ## After Hook. The compiler maps these 1:1 to Playwright test.beforeEach, the test() body wrapped in test.step() blocks, and registerTeardown / test.afterEach. Inline setup or cleanup mixed into ## Test Steps produces a malformed compiled spec.
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.
- 8d ago First seen · 253 lines · 32 tokens per session scan A 7006f32e7d97
author is a skill published in the GitHub repository Autodesk/claude-browser-test-skills (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 4,142 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 2026-08-31.
Other skills, from other repositories
glance-test
Run E2E browser tests on any web application using Glance MCP. Use when the user says "test this page," "check this URL," "run E2E tests," "browser test," "test the login flow," "check if the site works," "visual regression," or "screenshot this page." Also use for post-deploy verification and smoke tests.
reviewing-flows
Use when the pending flow queue needs triage before approval, such as deciding which recorded flows are worth keeping, clearing out ones that can never replay, or reading a flow's real steps before consenting to it.
flow-tester
End-to-end user journey tester using Playwright. Tests multi-step flows (signup, checkout, CRUD) with screenshots at each step. Auto-generates flows from URLs or text descriptions. Use after integration work to verify complete user journeys work.
playwright-tabbed-orchestration
Parent Agent uses playwright-tabbed to allocate browser tabs and partition tasks, then spawns child agents in parallel — each operating on its assigned tabid — for browser acceptance testing or automation, with a final aggregated summary. Suitable for multi-page validation, parallel module checks, and…
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
qprobe
QUESTPIE Probe — dev testing CLI for AI coding agents. Start servers, test APIs, control browsers via agent-browser, record and replay regression tests with zero tokens. Use when testing web apps, starting dev servers, reading logs, debugging errors, making API calls, checking browser console/network, or composing…