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 runnergit 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/runner)<a href="https://agentmods.dev/skills/autodesk/claude-browser-test-skills/runner"><img src="https://agentmods.dev/badge/skills/autodesk/claude-browser-test-skills/runner.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.01222 |
| Opus 5 | $0.00016 | $0.00611 |
| Sonnet 5 | $0.00007 | $0.00244 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
runner 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Test Runner
Overview
Executes a refined, stable E2E test case exactly as documented. No improvisation, no refinement - just faithful execution and clear pass/fail reporting.
Core principle: The test case is the source of truth. If a step fails, the test fails. Do not work around failures.
When to Use
- Running a previously refined test case
- User says "run the test" or "execute {test name}"
- CI-style validation of a known-good flow
Do NOT use when:
- No test case file exists (use
browser-test:author) - The test is known to be flaky (use
browser-test:refiner)
Prerequisites
- Stable test case file in
tests/e2e/{area}/ - The Playwright MCP server must be available (configured in
.mcp.json) - Dev server must be running (or
E2E_BASE_URLset to a reachable environment)
Process
1. Load test context
Read in order:
tests/e2e/conventions.md(global)tests/e2e/{area}/conventions.md(area)- The test case file
2. Environment gate
Read E2E_ENVIRONMENT from the environment (default: local). Check the test case's Environments line in preconditions. If the current environment is not listed, refuse to execute and report:
BLOCKED: {test name}
Reason: Test not allowed in "{environment}" (allowed: {environments list})
This is a hard stop - do not proceed, do not ask if the user wants to override.
3. Verify preconditions
Check each remaining precondition listed in the test case. If any are unmet, report and stop.
Read E2E_BASE_URL from the environment (default: http://localhost:5173). Use this value wherever the test references E2E_BASE_URL.
4. Set up fresh session
Follow Session Management from global conventions:
- Close any existing browser session (
browser_close) - Navigate to
E2E_BASE_URL- this starts a fresh browser instance - Verify clean session (cookie consent banner should appear on first navigation)
5. Execute steps
Execute the three hook sections in this order: ## Before Hook → ## Test Steps → ## After Hook . Validate the markdown has all three sections before starting — if any is missing, refuse to execute and report a malformed test case.
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 · 128 lines · 33 tokens per session scan A 58560ea6127f
runner 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 33 tokens to every session and 1,222 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…