nono AGENTS.md

nono AGENTS.md is an instructions file for Codex, OpenCode from nolabs-ai/nono. It costs 2,506 tokens per session, scanned A, original, Apache-2.0.

A development guide for nono, a Rust workspace that isolates untrusted AI agents in operating-system sandboxes.

In plain words
What is it for?
Use it when changing sandbox capabilities, security policies, command-line behaviour, C bindings, network filtering, or integration tests.
Why use it?
It clarifies the roles of the library, command-line tool, C interface, proxy, and test harness so changes go in the correct component.

Instructions file for CodexOpenCode

About the project

nono is a sandbox that gives AI agents controlled execution paths for running commands with limited privileges. It is used to let coding agents work while protecting credentials and production systems.

nolabs-ai/nono · 3,958 stars · on GitHub

Install

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.

agentmods
npx agentmods add instructions/nolabs-ai/nono/agents-md
Clone the repo
git clone --depth 1 https://github.com/nolabs-ai/nono

Made for: Codex, OpenCode.

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 nono AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nolabs-ai/nono/agents-md.svg)](https://agentmods.dev/instructions/nolabs-ai/nono/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nolabs-ai/nono/agents-md"><img src="https://agentmods.dev/badge/instructions/nolabs-ai/nono/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,506 This file is loaded in full into every session.
When invoked 2,506 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02506 $0.02506
Opus 5 $0.01253 $0.01253
Sonnet 5 $0.00501 $0.00501
Haiku 4.5 $0.00251 $0.00251

Measured 4d ago against content hash 1bc899507358, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nono 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 4d 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.

AGENTS.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nono - Development Guide

Project Overview

nono is a capability-based sandboxing system for running untrusted AI agents with OS-enforced isolation. It uses Landlock (Linux) and Seatbelt (macOS) to create sandboxes, and then layers on top a policy system, diagnostic tools, and a rollback mechanism for recovery. The library is designed to be a pure sandbox primitive with no built-in policy, while the CLI implements all security policy and UX.

The project is a Cargo workspace with five members:

  • nono (crates/nono/) - Core library. Pure sandbox primitive with no built-in security policy.
  • nono-cli (crates/nono-cli/) - CLI binary. Owns all security policy, profiles, hooks, and UX.
  • nono-ffi (bindings/c/) - C FFI bindings. Exposes the library via extern "C" functions and auto-generated nono.h header.
  • nono-proxy - Proxy that provides network filtering and credential injection
  • nono-test-support (crates/nono-test-support/) - Test-only harness for the nono-cli integration tests. Not published.

Library vs CLI Boundary

The library is a pure sandbox primitive. It applies ONLY what clients explicitly add to CapabilitySet:

In Library In CLI
CapabilitySet builder Policy groups (deny rules, dangerous commands, system paths)
Sandbox::apply() Group resolver (policy.rs) and platform-aware deny handling
SandboxState ExecStrategy (Direct/Monitor/Supervised)
DiagnosticFormatter Profile loading and hooks
QueryContext All output and UX
keystore learn mode
undo module (ObjectStore, SnapshotManager, MerkleTree, ExclusionFilter) Rollback lifecycle, exclusion policy, rollback UI

Build & Test

After every session, run these commands to verify correctness:

# Build everything
make build

# Run all tests
make test

# Full CI check (clippy + fmt + tests)
make ci

Individual targets:

make build-lib       # Library only
make build-cli       # CLI only
make test-lib        # Library tests only
make test-cli        # CLI tests only
make test-doc        # Doc tests only
make clippy          # Lint (strict: -D warnings -D clippy::unwrap_used)
make fmt-check       # Format check
make fmt             # Auto-format

Read the full file on GitHub · 213 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. 4d ago Changed · +7 lines · +97 tokens per session 1bc899507358
  2. 5d ago First seen · 206 lines · 2,409 tokens per session scan A f426a01a0383

Subscribe to this mod's changes

nono AGENTS.md is an instructions file published in the GitHub repository nolabs-ai/nono (3,958 stars, last pushed today), licensed Apache-2.0. It adds 2,506 tokens to every session, about $0.0125 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.