curupira: Instructions file for Claude Code

CLAUDE.md

curupira CLAUDE.md is an instructions file for Claude Code from drzln/curupira. It costs 2,652 tokens per session, scanned A, original, MIT.

A set of project instructions for Curupira, an MCP debugging server that connects an agent to Chrome's developer tools for debugging React applications. MCP is a protocol for connecting agents to external tools.

In plain words
What is it for?
Guide changes involving the Chrome connection, MCP handlers, server startup, dependency injection, and the project's shared TypeScript structure.
Why use it?
It gives coding work in the Curupira project consistent guidance about its architecture and implementation practices.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is drzln/curupira's own configuration. It tells Claude Code how to work on curupira itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything curupira configures โ†’

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **Context**: Apply general [Nexus Design Principles](../../../../CLAUDE.md) and [TypeScript Standards](../../../libraries/typescript/CLAUDE.md) to Curupira's Ch.

Reuse

Borrowing it

Nothing to install: this file belongs to drzln/curupira. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/drzln/curupira/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/drzln/curupira

Made for: Claude Code.

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 curupira CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/drzln/curupira/claude-md.svg)](https://agentmods.dev/instructions/drzln/curupira/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/drzln/curupira/claude-md"><img src="https://agentmods.dev/badge/instructions/drzln/curupira/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,652 This file is loaded in full into every session.
When invoked 2,652 The same file โ€” it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file โ€” 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 $0.02652 $0.02652
Opus 5 $0.01326 $0.01326
Sonnet 5 $0.00530 $0.00530
Haiku 4.5 $0.00265 $0.00265

Measured 7d ago against content hash d6c504f333b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

curupira CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured 7d 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.

CLAUDE.md ยท 429 lines

How it starts

The opening of the file, as written. The whole thing โ€” 429 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

Curupira MCP Debug Server

Context: Apply general Nexus Design Principles and TypeScript Standards to Curupira's Chrome DevTools Protocol + MCP bridge architecture.

๐ŸŽฏ Curupira-Specific Implementation

Curupira is an MCP debugging server that bridges Chrome DevTools Protocol with Model Context Protocol for React application debugging.

Architecture Overview

Chrome Browser โ†” CDP WebSocket โ†” Curupira Server โ†” MCP Protocol โ†” Claude

Curupira-Specific Hierarchy (Following Nexus Standards)

Level 0: Foundation        โ†’ Branded types, interfaces, configuration, errors
Level 1: Core Services     โ†’ Chrome service, repositories, buffer services  
Level 2: API Layer         โ†’ MCP handlers, resource/tool providers, transport
Level 3: Application       โ†’ Server bootstrap, dependency injection container

๐Ÿ”ง Chrome DevTools Protocol Integration

CDP Connection Management

// Branded types are defined in shared/src/types/branded.ts
import type { SessionId } from '@curupira/shared';

// Chrome service follows dependency injection pattern
export class ChromeService extends EventEmitter implements IChromeService {
  constructor(
    private readonly config: ChromeConfig,
    private readonly logger: ILogger,
    private readonly consoleBufferService?: IConsoleBufferService,
    networkBufferService?: INetworkBufferService
  ) {
    super();
  }

  async connect(options: ConnectionOptions): Promise<IChromeClient> {
    const client = new ChromeClient(this.logger, this.browserlessDetector, options);
    await client.connect();
    this.client = client;
    
    // Emit events for dynamic tool registration
    this.emit('connected', { client, options });
    
    return client;
  }
}

React Application Detection

// React detection implemented in integrations/react/detector.ts
export class ReactDetector {
  constructor(private logger: ILogger) {}
  
  async detect(client: IChromeClient, sessionId?: string): Promise<ReactInfo | null> {
    try {
      // Simplified detection using Runtime.evaluate
      const result = await client.send('Runtime.evaluate', {
        expression: 'typeof window.__REACT_DEVTOOLS_GLOBAL_HOOK__ !== "undefined"',
        returnByValue: true
      }, sessionId);
      
      if (result.result?.value === true) {
        return this.extractReactInfo(client, sessionId);
      }
      
      return null;
    } catch (error) {
      this.logger.debug({ error }, 'React detection failed');
      return null;
    }
  }
}

Read the full file on GitHub ยท 429 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. 7d ago First seen ยท 429 lines ยท 2,652 tokens per session scan A d6c504f333b4

Subscribe to this mod's changes

curupira CLAUDE.md is an instructions file published in the GitHub repository drzln/curupira (0 stars, last pushed 4mo ago), licensed MIT. It adds 2,652 tokens to every session, about $0.0133 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 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.

openai/codex ยท 5,182 tokens

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).

microsoft/vscode ยท 6,785 tokens

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.

vercel/next.js ยท 7,296 tokens

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.

langchain-ai/langchain ยท 4,469 tokens

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).

microsoft/vscode ยท 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart โ€” add a new integration in 5 steps, integration architecture and integrationmanifest โ€” file tracking.

github/spec-kit ยท 7,104 tokens