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/nutthouse/tutti/claude-mdgit clone --depth 1 https://github.com/nutthouse/tuttiWhat 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 | $0.00824 | $0.00824 |
| Opus 5 | $0.00412 | $0.00412 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
tutti 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 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutti — Project Conventions
Language & Tooling
- Rust (stable), single crate, binary name
tt - No async in Phase 1 — all tmux interaction is synchronous
std::process::Command - Dependencies: clap (derive), serde + toml, thiserror, comfy-table, colored, chrono, which
Architecture
src/cli/— Clap command handlers, one file per subcommandsrc/config/— TOML config types and parsing (includes role mapping +[roles]table)src/runtime/— RuntimeAdapter trait + per-runtime implementationssrc/session/— tmux session management wrapperssrc/worktree/— Git worktree lifecyclesrc/state/— .tutti/ directory and agent state persistencesrc/template/— Template pack parsing, generation, repo detection, and built-in templatessrc/automation/— Workflow execution engine, artifact pipeline, artifact-polling modesrc/permissions/— Claude Code settings generation and shell policy shimssrc/error.rs— Central error types via thiserror
Naming
- Musical terminology: voices (running agents), arrangements (configs), movements (phases), phrases (prompts)
- tmux sessions:
tutti-{team}-{agent} - Git branches for worktrees:
tutti/{agent} - State files:
.tutti/state/{agent}.json
Testing
- Unit tests in each module (
#[cfg(test)] mod tests) - Integration tests that need tmux should check for its presence first
- Use
tempfileorstd::env::temp_dir()for filesystem tests
Error Handling
- All public functions return
Result<T, TuttiError> - Use
thiserrorfor error variants, not anyhow - User-facing errors should include actionable guidance
Style
cargo fmtandcargo clippymust pass (CI enforced)- Prefer explicit imports over glob imports
- Keep functions focused — if it's doing two things, split it
Code Review (CodeRabbit)
- CodeRabbit is configured as a required reviewer on PRs
- When it finds issues, it submits a "Request changes" review to block merging
- Once all CodeRabbit comments are resolved and pre-merge checks pass, it automatically switches to "Approve"
- Do not manually dismiss CodeRabbit reviews — fix the issues and let it re-review
- PRs are only mergeable when CodeRabbit approves AND all CI checks are green
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 · 65 lines · 824 tokens per session scan A 5048ccd4f927
tutti CLAUDE.md is an instructions file published in the GitHub repository nutthouse/tutti (116 stars, last pushed 1mo ago), licensed MIT. It adds 824 tokens to every session, about $0.0041 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.
Other instructions, from other repositories
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).
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.
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.