Tutti is a real-time collaboration space where people can work alongside multiple AI agents, including by sharing rooms, editing together, and borrowing agents. It is intended for users who want human-agent or multi-agent collaboration across devices, with open-source and VM versions available. The catalogue entries provide skills and instructions for working with Tutti.
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/tutti-os/tutti/agents-mdgit clone --depth 1 https://github.com/tutti-os/tuttiWrote 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/tutti-os/tutti/agents-md)<a href="https://agentmods.dev/instructions/tutti-os/tutti/agents-md"><img src="https://agentmods.dev/badge/instructions/tutti-os/tutti/agents-md.svg" alt="Measured on agentmods" 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 | $0.02302 | $0.02302 |
| Opus 5 | $0.01151 | $0.01151 |
| Sonnet 5 | $0.00460 | $0.00460 |
| Haiku 4.5 | $0.00230 | $0.00230 |
Grade A, and why
tutti 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 5d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Shape
tutti is a local-first desktop monorepo.
services/tuttid: daemon product rules, durable local state, HTTP/query, and adapterspackages/agent/host: provider-neutral agent lifecycle application coreapps/desktop: Electron shell, preload, renderer UI, desktop integrationpackages/clients/*: generated and hand-written domain clientspackages/configs/*: shared TypeScript and formatting configconfig: sources used to generate runtime defaults
Keep daemon/product-specific business logic in services/tuttid; keep extracted cross-consumer application cores in their owning package. Do not let apps/desktop become a second business core. Do not create vague packages such as shared, common, utils, or client-sdk.
Routing
Read the closest AGENTS.md before editing:
apps/desktop/*->apps/desktop/AGENTS.mdservices/tuttid/*->services/tuttid/AGENTS.mdpackages/agent/gui/*->packages/agent/gui/AGENTS.mdpackages/connector/*->packages/connector/AGENTS.mdpackages/agent/session-replay/*->packages/agent/session-replay/AGENTS.mdpackages/ui/*->packages/ui/AGENTS.mdpackages/*->packages/AGENTS.md
Use this root file for repository-wide defaults only. Area-specific files win.
Route agent application-core requests to packages/agent/host first. If a
request mentions agent session, turn, goal, or runtime-operation lifecycle,
creation, resume, send, cancel, recovery, or the agent host boundary, read
packages/agent/host/README.md and the Agent Host Boundary section below
before planning or editing, then the nearest area AGENTS.md.
Also route by module name, not only by path. If a request mentions AgentGUI,
AgentGuiNode, Agent GUI, the agent conversation module, agent composer,
workspace agent timeline, agent approvals, or interactive agent prompts, read
docs/architecture/agent-gui-node.md first, then
packages/agent/gui/AGENTS.md, before planning or editing, even when no file
path is supplied.
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.
- 5d ago First seen · 187 lines · 2,302 tokens per session scan A cd869a819816
tutti AGENTS.md is an instructions file published in the GitHub repository tutti-os/tutti (3,684 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,302 tokens to every session, about $0.0115 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
babysitter AGENTS.md
AGENTS.md instructions for a5c-ai/babysitter, covering agents.md, repo-specific overrides, reference map and quick commands.
agenta AGENTS.md
AGENTS.md instructions for Agenta-AI/agenta, covering contributor guide, repo map, where conventions live, branching and prs with gitbutler and before committing.
team AGENTS.md
AGENTS.md instructions for bostonaholic/team, covering agents.md: project router, what this is, runtime vs. development, design philosophy and pipeline.
babysitter CLAUDE.md
Claude Code instructions for a5c-ai/babysitter, covering claude.md, repo-specific overrides, read these first, quick commands and claude code local notes.
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.