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 refinergit 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/refiner)<a href="https://agentmods.dev/skills/autodesk/claude-browser-test-skills/refiner"><img src="https://agentmods.dev/badge/skills/autodesk/claude-browser-test-skills/refiner/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/refiner"><img src="https://agentmods.dev/badge/skills/autodesk/claude-browser-test-skills/refiner.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 | $0.00039 | $0.01785 |
| Opus 5 | $0.00019 | $0.00892 |
| Sonnet 5 | $0.00008 | $0.00357 |
| Haiku 4.5 | $0.00004 | $0.00178 |
Grade A, and why
refiner 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 9d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Test Refiner
Overview
Takes a structured test case and makes it deterministic by running it repeatedly, identifying failure patterns, and refining both the test case and shared conventions. Stops when N consecutive runs pass without the runner deviating from the documented steps.
Core principle: A test isn't done until it passes N times in a row with identical execution. Every workaround discovered belongs in the test case or conventions, not in the runner's head.
When to Use
- A new test case was just authored (handoff from
browser-test:author) - An existing test is flaky or inconsistent
- User says "stabilize this test" or "make this test reliable"
Do NOT use when:
- No structured test case exists yet (use
browser-test:authorfirst) - A stable test just needs to be executed (use
browser-test:runner)
Prerequisites
- Structured test case file exists 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
digraph refiner_flow {
rankdir=TB;
"Read test case + conventions" -> "Execute test (fresh session)";
"Execute test (fresh session)" -> "Pass?" [label="run"];
"Pass?" -> "Analyze failure" [label="no"];
"Analyze failure" -> "Update test or conventions" [label="pattern identified"];
"Update test or conventions" -> "Execute test (fresh session)" [label="reset counter"];
"Pass?" -> "N consecutive passes?" [label="yes"];
"N consecutive passes?" -> "Execute test (fresh session)" [label="no, keep going"];
"N consecutive passes?" -> "Done - test is stable" [label="yes"];
}
1. Read the test case and conventions
Read the test case file, global conventions, and area conventions. Understand every step before running.
Check the test's Environments line against E2E_ENVIRONMENT (default: local). If the current environment is not listed, refuse to execute. Use E2E_BASE_URL (default: http://localhost:5173) wherever the test references it.
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.
- 9d ago First seen · 122 lines · 39 tokens per session scan A 30cfec35f284
refiner 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 39 tokens to every session and 1,785 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-e2e-testing
Production-grade Playwright end-to-end testing skill for AI coding agents. Provides specialized guidance for writing, debugging, and maintaining Playwright tests in TypeScript, JavaScript, and Python. Covers the full testing lifecycle: test structure and architecture (Page Object Model, fixtures, custom matchers)…
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.