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/pcomans/caruso/agents-mdgit clone --depth 1 https://github.com/pcomans/carusoWhat 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 | $0.02820 | $0.02820 |
| Opus 5 | $0.01410 | $0.01410 |
| Sonnet 5 | $0.00564 | $0.00564 |
| Haiku 4.5 | $0.00282 | $0.00282 |
Grade A, and why
caruso AGENTS.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 2d 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 — 273 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.
Mission
Caruso is a Ruby gem CLI that bridges the gap between AI coding assistants. It fetches "steering documentation" (commands, agents, skills) from Claude Code Marketplaces and converts them to formats compatible with other IDEs, currently Cursor.
Source of Truth: Official Documentation
IMPORTANT: The authoritative sources for Claude Code and Cursor specifications are the official docs. Reference links are in /Users/philipp/code/caruso/reference/:
claude_code.md- Links to official Claude Code docs (hooks, plugins, marketplaces, skills)cursor.md- Links to official Cursor docs (hooks, modes, rules, commands)
When implementing features or fixing bugs, always fetch the latest docs from these official URLs. If the implementation conflicts with the official docs, the docs are correct and the code should be updated to match.
Development Commands
Build and Install
# Build the gem
gem build caruso.gemspec
# Install locally
gem install caruso-*.gem
# Verify installation
caruso version
Testing
# Run offline tests only (default)
bundle exec rake spec
# or
bundle exec rspec
# Run all tests including live marketplace integration
bundle exec rake spec:all
# or
RUN_LIVE_TESTS=1 bundle exec rspec
# Run only live tests
bundle exec rake spec:live
# Run specific test file
bundle exec rspec spec/integration/plugin_spec.rb
# Run specific test
bundle exec rspec spec/integration/plugin_spec.rb:42
Important: Live tests (tagged with :live) interact with real marketplaces (anthropics/skills) and require network access. They can be slow (~7 minutes). Marketplace cache is stored in ~/.caruso/marketplaces/. Integration tests set CARUSO_TESTING_SKIP_CLONE=true to skip Git cloning for fast offline testing.
Linting
bundle exec rubocop
Version Management
# Bump patch version (0.1.3 → 0.1.4)
bundle exec rake bump:patch
# Bump minor version (0.1.4 → 0.2.0)
bundle exec rake bump:minor
# Bump major version (0.1.4 → 1.0.0)
bundle exec rake bump:major
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.
- 2d ago First seen · 273 lines · 2,820 tokens per session scan A 356097be1f31
caruso AGENTS.md is an instructions file published in the GitHub repository pcomans/caruso (3 stars, last pushed 4mo ago), licensed MIT. It adds 2,820 tokens to every session, about $0.0141 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.
Other instructions, from other repositories
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.
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).
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.