Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Autodesk/claude-browser-test-skillsnpx agentmods add skills/autodesk/claude-browser-test-skills/compilerWrote 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/compiler)<a href="https://agentmods.dev/skills/autodesk/claude-browser-test-skills/compiler"><img src="https://agentmods.dev/badge/skills/autodesk/claude-browser-test-skills/compiler.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 | $0.00055 | $0.12879 |
| Opus 5 | $0.00028 | $0.06439 |
| Sonnet 5 | $0.00011 | $0.02576 |
| Haiku 4.5 | $0.00006 | $0.01288 |
Grade A, and why
compiler 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 — 722 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Test Compiler
Overview
Converts a refined markdown E2E test case into a Playwright .spec.ts file by replaying the test in a live browser session and recording every selector from browser_snapshot — never from reading application source code.
Core principle: Every selector in the compiled output must come from a live browser snapshot. Static code analysis produces brittle, untested selectors. The browser is the source of truth.
When to Use
- A markdown test case has been refined and is stable (passed consecutive browser-use runs)
- User says "compile this test", "convert to playwright", or "generate spec from markdown"
- Batch compilation of multiple stable test cases
Do NOT use when:
- No test case file exists (use
browser-test:author) - Test case hasn't been refined/stabilized (use
browser-test:refiner) - Test is known to be flaky (refine first)
- Test involves complex dynamic behavior that can't be captured in static code (rare)
Prerequisites
- Stable, refined markdown test case in
tests/e2e/{area}/ - Playwright MCP server available (configured in
.mcp.json) - Dev server running (or
E2E_BASE_URLset to a reachable environment) - Existing
playwright-tests/structure with utils and fixtures
Process
1. Load Context
Read in order:
tests/e2e/conventions.md(global conventions)tests/e2e/{area}/conventions.md(area conventions)- The markdown test case to compile
playwright-tests/utils/INVENTORY.mdandplaywright-tests/journeys/{area}/INVENTORY.md(utility inventories — run bootstrapping if global inventory absent; run staleness check against referenced.tsfiles before proceeding). Also loadplaywright-tests/locators/INVENTORY.mdif it exists — this tracks all locator objects separately from action utilities. Additionally, scan the actual.tsfiles directly — do not rely solely on INVENTORY.md:- Glob
playwright-tests/utils/**/*.tsand extract all exportedasync functionsignatures - Glob
playwright-tests/locators/**/*.tsand extract all exportedconstobjects + their method signatures This catches utilities that exist in.tsfiles but are not yet documented in INVENTORY.md. Any undocumented utility found this way is treated as an existing utility for the purpose of Step 4 (use it if it matches) and is flagged for inventory documentation in the Step 6 report (Step 6: Inventory Write Protocol → Auto-detection).
- Glob
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 · 722 lines · 55 tokens per session scan A 0d1e7b3477bd
compiler 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 55 tokens to every session and 12,879 once invoked, about $0.0003 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
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)…
ESLint for Test Quality
Enforce test quality with ESLint - eslint-plugin-jest, eslint-plugin-playwright, and eslint-plugin-testing-library rules in flat config, blocking focused tests, missing assertions, and flaky waits via a CI lint gate.
typescript-e2e-testing
E2E and integration testing for TypeScript/NestJS projects using Jest, supertest, and real infrastructure via Docker (Kafka, PostgreSQL, MongoDB, Redis) with the Given-When-Then pattern. Use whenever the user is working on .e2e-spec.ts files or anything under test/e2e/, or asks to set up, write, review, run, debug, or…
author
Rules for writing Playwright .spec.ts files that don't flake — selector hygiene, auto-wait discipline, idempotent fixtures, readable trace output. Used by /e2e:write, /e2e:record, and the e2e:spec-writer subagent.
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.