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 agentmods add instructions/microsoft/playwright/claude-mdgit clone --depth 1 https://github.com/microsoft/playwrightWhat 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 | $0.01902 | $0.01902 |
| Opus 5 | $0.00951 | $0.00951 |
| Sonnet 5 | $0.00380 | $0.00380 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
playwright CLAUDE.md 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 yesterday.
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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monorepo Packages
| Package | npm name | Purpose |
|---|---|---|
playwright-core |
playwright-core |
Browser automation engine: client, server, dispatchers, protocol |
playwright |
playwright |
Test runner + browser automation (public package) |
playwright-test |
@playwright/test |
Test runner entry point |
playwright-client |
@playwright/client |
Standalone client package |
protocol |
(internal) | RPC protocol definitions (protocol.yml → generated channels.d.ts) |
Browser Packages
playwright-chromium, playwright-firefox, playwright-webkit — per-browser distributions.
playwright-browser-chromium, playwright-browser-firefox, playwright-browser-webkit — binary packages.
Tooling Packages
| Package | Purpose |
|---|---|
html-reporter |
HTML test report viewer |
trace-viewer |
Trace viewer UI |
recorder |
Test recorder |
web |
Shared web UI components |
injected |
Scripts injected into browser pages |
Key Directories
| Directory | Purpose |
|---|---|
tests/ |
All test suites (page, library, playwright-test, mcp, etc.) |
docs/src/ |
API documentation — source of truth for public TypeScript types |
docs/src/api/ |
Per-class API reference (class-page.md, class-locator.md, etc.) |
utils/ |
Build scripts, code generation, linting, doc tools |
browser_patches/ |
Browser engine patches |
Build
npm run build # Full build
npm run watch # Watch mode (recommended during development)
Assume watch is running and code is up to date. Generated files (types, channels, validators) are produced by watch automatically.
Lint and type check
npm run flint
Runs all lint checks in parallel: eslint, tsc, doclint, check-deps, generate_channels, generate_types, lint-tests, test-types, lint-packages, code-snippet linting.
Always run flint before committing. Do not use tsc --noEmit or individual lint commands separately.
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.
- yesterday First seen · 165 lines · 1,902 tokens per session scan A 99809538a469
playwright CLAUDE.md is an instructions file published in the GitHub repository microsoft/playwright (95,378 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,902 tokens to every session, about $0.0095 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 2026-08-30.
Other instructions, from other repositories
claude-browser-test-skills CLAUDE.md
Instructions for Autodesk/claude-browser-test-skills, covering claude.md, what this repo is, layout, conventions when editing skills and validate before publishing.
playwright-fieldkit AGENTS.md
Instructions for jpbaking/playwright-fieldkit: Follow the Portable Agent Authoring guides for every skill or harness change.
AI-Watch-Tester CLAUDE.md
Instructions for ksgisang/AI-Watch-Tester, covering aat (ai auto tester) — project guide, ⛔ awt testing workflow (필수 준수), step 1: scan, step 2: generate + present and step 3: execute (승인 후에만).
lambda CLAUDE.md
Instructions for adriancarriger/lambda, covering lambda - multi-agent development, tmux windows, personality, sample app and e2e tests.
playwright-fieldkit CLAUDE.md
Instructions for jpbaking/playwright-fieldkit, a project described as: Playwright FieldKit: gives coding agents hands and eyes on the web — crawl, debug, record, and test live sites via deterministic scripts; portable Agent Skill for Codex, Claude Code, Antigravity, and Cline.
playwriter AGENTS.md
Instructions for remorses/playwriter, covering backward compatibility, architecture, development, running mcp locally and running cli locally.