compiler

compiler is a skill for Claude Code from Autodesk/claude-browser-test-skills. It costs 55 tokens per session (12,879 once invoked), scanned A, original, Apache-2.0.

A tool that turns a stable Markdown browser-test description into a Playwright test file ending in .spec.ts.

In plain words
What is it for?
Use it to convert a refined end-to-end test into executable Playwright code, including batch conversion of multiple stable test cases.
Why use it?
It records selectors from the running browser, which helps avoid test code based on assumptions about the application’s source code.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is // ... utility imports as needed (note: ../../utils/ for action utilities/helpers, ../../locators/ for locator objects, ../../fixtures/ for test data — all two .

Part of the browser-test plugin — 4 skills shipped together

Good fit Use it to convert a refined end-to-end test into executable Playwright code, including batch conversion of multiple stable test cases.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Autodesk/claude-browser-test-skills
agentmods
npx agentmods add skills/autodesk/claude-browser-test-skills/compiler

Made for: Claude Code.

Or install browser-test, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for compiler

README.md
[![agentmods](https://agentmods.dev/badge/skills/autodesk/claude-browser-test-skills/compiler.svg)](https://agentmods.dev/skills/autodesk/claude-browser-test-skills/compiler)
Your own site
<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>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,879 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 0d1e7b3477bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

skills/compiler/SKILL.md · 722 lines

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_URL set to a reachable environment)
  • Existing playwright-tests/ structure with utils and fixtures

Process

1. Load Context

Read in order:

  1. tests/e2e/conventions.md (global conventions)
  2. tests/e2e/{area}/conventions.md (area conventions)
  3. The markdown test case to compile
  4. playwright-tests/utils/INVENTORY.md and playwright-tests/journeys/{area}/INVENTORY.md (utility inventories — run bootstrapping if global inventory absent; run staleness check against referenced .ts files before proceeding). Also load playwright-tests/locators/INVENTORY.md if it exists — this tracks all locator objects separately from action utilities. Additionally, scan the actual .ts files directly — do not rely solely on INVENTORY.md:
    • Glob playwright-tests/utils/**/*.ts and extract all exported async function signatures
    • Glob playwright-tests/locators/**/*.ts and extract all exported const objects + their method signatures This catches utilities that exist in .ts files 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).

Read the full file on GitHub · 722 lines

Changes

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.

  1. 8d ago First seen · 722 lines · 55 tokens per session scan A 0d1e7b3477bd

Subscribe to this mod's changes

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.

Related

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)…

JPeetz/agent-skills · 316 tokens

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.

PramodDutta/qaskills · 50 tokens

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…

bmad-labs/skills · 122 tokens

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.

alphabravo-oss/guild · 61 tokens

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.

DebugBase/glance · 80 tokens

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.

m4ttstack/fast-browser · 46 tokens