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-mcp/claude-mdgit clone --depth 1 https://github.com/microsoft/playwright-mcpWhat 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 | $0.00363 | $0.00363 |
| Opus 5 | $0.00181 | $0.00181 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
playwright-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
5 near-identical copies found in the catalogue:
- oss-playwright-mcp CLAUDE.md — 100% identical, 0 lines differ
- Playwright-Mcp1 CLAUDE.md — 100% identical, 0 lines differ
- playwright-mcp-render-mt8x2ig6 CLAUDE.md — 100% identical, 0 lines differ
- MCP_DOCS CLAUDE.md — 100% identical, 0 lines differ
- MCP_docs CLAUDE.md — 100% identical, 0 lines differ
What it actually says
Commit Convention
Semantic commit messages: label(scope): description
Labels: fix, feat, chore, docs, test, devops
git checkout -b fix-39562
# ... make changes ...
git add <changed-files>
git commit -m "$(cat <<'EOF'
fix(proxy): handle SOCKS proxy authentication
Fixes: https://github.com/microsoft/playwright/issues/39562
EOF
)"
git push origin fix-39562
gh pr create --repo microsoft/playwright --head username:fix-39562 \
--title "fix(proxy): handle SOCKS proxy authentication" \
--body "$(cat <<'EOF'
## Summary
- <describe the change very! briefly>
Fixes https://github.com/microsoft/playwright/issues/39562
EOF
)"
Never add Co-Authored-By agents in commit message.
Branch naming for issue fixes: fix-<issue-number>
Rolling Playwright
- Run
node roll.js(ornpm run roll) to bumpplaywright,playwright-core, and@playwright/test, refreshconfig.d.ts, and regenerate the README. The script prints the resolved version — use its suffix for the branch name. - Create a branch:
git checkout -b roll-pw-<version-suffix>. - Run
npm test. Only proceed if all tests pass. - Commit with
chore: roll Playwright to <version>, push, and open a PR againstmicrosoft/playwright-mcpwith the same title.
Preparing a Release
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.
- 3d ago First seen · 42 lines · 363 tokens per session scan A e4cf26b7670c
playwright-mcp CLAUDE.md is an instructions file published in the GitHub repository microsoft/playwright-mcp (36,714 stars, last pushed 2d ago), licensed Apache-2.0. It adds 363 tokens to every session, about $0.0018 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
argus AGENTS.md
Instructions for chriswu727/argus, covering argus — agent guide, setup, web mode (works everywhere), wire it into the mcp host and using argus within the host task.
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.
AI-Watch-Tester AGENTS.md
Instructions for ksgisang/AI-Watch-Tester, covering awt (ai watch tester) — ai agent rules, ⛔ mandatory workflow — 4 steps, no exceptions, step 1: scan, step 2: generate + present and step 3: execute (only after user says "go ahead").
claude-code-playwright-mcp-test CLAUDE.md
Claude Code instructions for terryso/claude-code-playwright-mcp-test, covering claude test framework - demo project, prerequisites, for new projects (recommended), for this demo project and available commands.
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.