claude-cruise: Instructions file for Claude Code

CLAUDE.md

claude-cruise CLAUDE.md is an instructions file for Claude Code from amitlals/claude-cruise. It costs 639 tokens per session, scanned A, original, MIT.

Project guidance for Claude Cruise, a proxy for Claude Code that tracks usage and routes requests to backup providers when limits are near. It covers development commands and the main proxy, prediction, and routing components.

In plain words
What is it for?
Use it when developing, building, testing, or changing request tracking, rate-limit prediction, provider routing, the HTTP server, or its terminal dashboard.
Why use it?
It helps a coding agent work within the project’s architecture and verify changes before running the proxy.

Instructions file for Claude Code

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

This is amitlals/claude-cruise's own configuration. It tells Claude Code how to work on claude-cruise 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 claude-cruise configures →

Reuse

Borrowing it

Nothing to install: this file belongs to amitlals/claude-cruise. 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/amitlals/claude-cruise/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/amitlals/claude-cruise

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 claude-cruise CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/amitlals/claude-cruise/claude-md/github.svg)](https://agentmods.dev/instructions/amitlals/claude-cruise/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/amitlals/claude-cruise/claude-md"><img src="https://agentmods.dev/badge/instructions/amitlals/claude-cruise/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.

agentmods 80×15 button for claude-cruise CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/amitlals/claude-cruise/claude-md"><img src="https://agentmods.dev/badge/instructions/amitlals/claude-cruise/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 639 This file is loaded in full into every session.
When invoked 639 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — 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 $0.00639 $0.00639
Opus 5 $0.00319 $0.00319
Sonnet 5 $0.00128 $0.00128
Haiku 4.5 $0.00064 $0.00064

Measured 10d ago against content hash b01b49962525, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-cruise 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 10d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Claude Cruise is a smart proxy for Claude Code that prevents rate limits by predicting usage patterns and automatically routing requests to fallback providers (Haiku, OpenRouter, Ollama) when approaching quotas.

Development Commands

# Development (runs tsx with React/Ink terminal UI)
npm run dev

# Build TypeScript to dist/
npm run build

# Run built version
npm start

# Type checking
npm run typecheck

# Run tests
npm test

Architecture

Core Modules

  • src/proxy/server.ts - Hono-based HTTP proxy server that intercepts Claude API calls, logs usage, and serves the web dashboard. Handles both streaming and non-streaming responses.

  • src/predictor/index.ts - Rate limit prediction engine with three components:

    • RateLimitTracker - Learns actual limits from 429 errors
    • VelocityCalculator - Calculates usage rate and detects patterns (burst/steady/declining)
    • PredictionEngine - Predicts when limits will be hit based on learned limits and velocity
  • src/router/index.ts - Smart routing with threshold-based model switching:

    • 0-70%: Use requested model (Sonnet)
    • 70-85%: Switch to Haiku (73% cheaper)
    • 85-95%: Switch to OpenRouter
    • 95%+: Switch to Ollama (local, free)
  • src/storage/database.ts - SQLite persistence using better-sqlite3. Stores usage logs, rate limit events, routing decisions, and sessions. Data stored in ~/.cruise/usage.db.

  • src/cli/index.tsx - Terminal UI built with Ink (React for CLI). Renders dashboard with usage gauges, predictions, and routing status.

Data Flow

  1. Claude Code sends request to proxy (localhost:4141)
  2. Router checks prediction engine for current usage %
  3. Request routed to appropriate provider based on thresholds
  4. Response streamed back, usage logged to SQLite
  5. On 429 error, predictor learns and router activates fallback

Read the full file on GitHub · 75 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. 10d ago First seen · 75 lines · 639 tokens per session scan A b01b49962525

Subscribe to this mod's changes

claude-cruise CLAUDE.md is an instructions file published in the GitHub repository amitlals/claude-cruise (11 stars, last pushed 1mo ago), licensed MIT. It adds 639 tokens to every session, about $0.0032 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.

Related

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.

vercel/next.js · 7,296 tokens

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 · 5,153 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 · 6,785 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 · 5,001 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 · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens