Borrowing it
Nothing to install: this file belongs to EndeavorYen/chrome-cdp-ex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/EndeavorYen/chrome-cdp-ex/main/CLAUDE.mdgit clone --depth 1 https://github.com/EndeavorYen/chrome-cdp-exWrote 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/instructions/endeavoryen/chrome-cdp-ex/claude-md)<a href="https://agentmods.dev/instructions/endeavoryen/chrome-cdp-ex/claude-md"><img src="https://agentmods.dev/badge/instructions/endeavoryen/chrome-cdp-ex/claude-md.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 | $0.01015 | $0.01015 |
| Opus 5 | $0.00508 | $0.00508 |
| Sonnet 5 | $0.00203 | $0.00203 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
chrome-cdp-ex 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 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — chrome-cdp-ex
TL;DR — The product runtime is
skills/chrome-cdp-ex/scripts/cdp.mjs, supported by focused helpers inscripts/lib/and a stdio MCP adapter. Preserve the zero-runtime-dependency design, structured handoff contracts, privacy defaults, and evidence-first workflow.
Problem-Solving Principles
These principles are non-negotiable and apply to every task in this repository.
- Root cause first — When encountering an error, trace it to the root cause. Never paper over issues with workarounds. "It seems to work" ≠ "correctly fixed."
- Admit uncertainty — If you don't know the root cause, say "I'm not sure" rather than inventing a plausible but unverified explanation.
- Challenge your own answers — Always ask: Is this the best solution? Can it be better? Is there a fundamentally better approach?
- Be honest, not agreeable — The most valuable response is the correct one, not the one that flatters the user. Push back when the user's direction is suboptimal.
Project Overview
This is a Claude Code plugin and portable agent skill that gives LLM agents direct access to the user's running Chrome browser via the Chrome DevTools Protocol (CDP). It connects to existing browser sessions with login state, cookies, and open tabs; Playwright remains the better choice for clean deterministic test browsers.
- Command runtime:
skills/chrome-cdp-ex/scripts/cdp.mjs. - Focused helpers:
skills/chrome-cdp-ex/scripts/lib/owns action recovery, receipt surfaces, perception models, reports, page/screenshot/responsive health, target binding, and MCP mapping. - MCP server:
skills/chrome-cdp-ex/scripts/mcp-server.mjsmaps stdio MCP calls to the same CLI runtime. - Skill definition:
skills/chrome-cdp-ex/SKILL.mdis the always-loaded golden path; exhaustive command docs live inskills/chrome-cdp-ex/references/. - Plugin manifest:
.claude-plugin/plugin.jsonmust matchpackage.jsonversion metadata. - Runtime dependencies: Node.js 22+ and built-ins only; npm packages are development/test tooling.
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 · 76 lines · 1,015 tokens per session scan A fe21d73ac3eb
chrome-cdp-ex CLAUDE.md is an instructions file published in the GitHub repository EndeavorYen/chrome-cdp-ex (20 stars, last pushed 5d ago), licensed MIT. It adds 1,015 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.