Borrowing it
Nothing to install: this file belongs to VitalyOstanin/mcp-chrome-debugger-protocol. 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/VitalyOstanin/mcp-chrome-debugger-protocol/master/CLAUDE.mdgit clone --depth 1 https://github.com/VitalyOstanin/mcp-chrome-debugger-protocolWrote 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/vitalyostanin/mcp-chrome-debugger-protocol/claude-md)<a href="https://agentmods.dev/instructions/vitalyostanin/mcp-chrome-debugger-protocol/claude-md"><img src="https://agentmods.dev/badge/instructions/vitalyostanin/mcp-chrome-debugger-protocol/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/vitalyostanin/mcp-chrome-debugger-protocol/claude-md"><img src="https://agentmods.dev/badge/instructions/vitalyostanin/mcp-chrome-debugger-protocol/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01105 | $0.01105 |
| Opus 5 | $0.00553 | $0.00553 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade B, and why
mcp-chrome-debugger-protocol CLAUDE.md scanned grade B with 1 finding 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 9d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- **Follow ESLint rules strictly** - write code that passes linting without warnings, use `??` instead of `||`, avoid unused variables, prefer explicit types How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Memory for MCP Chrome Debugger Protocol
Also read
AGENTS.md(Repository Guidelines) for contributor instructions and day-to-day workflow.
Project Rules
- ABSOLUTELY NEVER use
anytype anywhere in TypeScript code - always use proper typing, create interfaces, use unknown with type guards, or use generic types - Use official types from modules instead of custom types - import and use existing types from @modelcontextprotocol/sdk and other modules rather than creating custom interfaces
- NEVER use emoji in code, comments, or console output - keep all text plain and professional
- Always return JSON from MCP tools instead of user-friendly strings
- Use filePath parameter for breakpoints, not scriptId
- Maintain consistent error handling patterns
- Apply DRY (Don't Repeat Yourself) principle everywhere except in tests - extract common patterns, shared utilities, and reusable functions
- Use modern ES features - prefer const/let over var, arrow functions, async/await, destructuring, optional chaining, nullish coalescing
- Use Node.js built-in promise-based APIs - prefer
node:timers/promisesover setTimeout,node:fs/promisesover callback fs methods - ABSOLUTELY MANDATORY: Use modern Promise-based timers with async/await - always use
import { setTimeout } from "node:timers/promises"and async/await patterns instead of callback-based setTimeout - ABSOLUTELY MANDATORY: NEVER use
JSON.stringifyinsrc/*- use the safe version (safe-stable-stringify) -import safeStringify from "safe-stable-stringify"and callsafeStringify(value)everywhere. The safe version handles circular references, gives deterministic key order, and matches the project's wire-format guarantees. This rule applies to cache keys, log messages, MCP wire format, and any other serialization. The only allowed exception is template strings that are injected into the debuggee runtime via CDPRuntime.evaluate(where safe-stable-stringify is not available); document such exceptions inline.JSON.parseremains allowed for incoming JSON. - Follow ESLint rules strictly - write code that passes linting without warnings, use
??instead of||, avoid unused variables, prefer explicit types - No community docs until there is a community - do NOT add
CONTRIBUTING.mdorCODE_OF_CONDUCT.md. While the project has no external contributor community, these files are unnecessary; contributor guidance lives inAGENTS.mdand the README Development section.
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.
- 9d ago First seen · 61 lines · 1,105 tokens per session scan B 9fc3796f2af0
mcp-chrome-debugger-protocol CLAUDE.md is an instructions file published in the GitHub repository VitalyOstanin/mcp-chrome-debugger-protocol (2 stars, last pushed 2d ago), licensed MIT. It adds 1,105 tokens to every session, about $0.0055 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.