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.
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/nolabs-ai/nono/agents-mdgit clone --depth 1 https://github.com/nolabs-ai/nonoWrote 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/nolabs-ai/nono/agents-md)<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>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 | $0.02506 | $0.02506 |
| Opus 5 | $0.01253 | $0.01253 |
| Sonnet 5 | $0.00501 | $0.00501 |
| Haiku 4.5 | $0.00251 | $0.00251 |
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.
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 viaextern "C"functions and auto-generatednono.hheader. - nono-proxy - Proxy that provides network filtering and credential injection
- nono-test-support (
crates/nono-test-support/) - Test-only harness for thenono-cliintegration 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
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.
- 4d ago Changed · +7 lines · +97 tokens per session 1bc899507358
- 5d ago First seen · 206 lines · 2,409 tokens per session scan A f426a01a0383
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.
Other instructions, from other repositories
ai-appsec AGENTS.md
Instructions for subodhkc/ai-appsec, covering agents.md — haiec agent security mcp (phase -1 → phase 18), 1. workspace layout, 2. architectural principles (apply to every phase), 3. hard constraints (never violate) and 4. phase discipline.
stride-gpt AGENTS.md
AGENTS.md instructions for mrwadams/stride-gpt, covering agents.md, what this project is, repository layout, how the agentic analysis works and progressive disclosure pattern.
.context copilot-instructions.md
Copilot instructions for forefy/.context: This repo contains instruction files for using and conducting security reviews, do not confuse this copilot-instructions.md from other copilot-instructions files existing in this workspace.
sprites-ex CLAUDE.md
Claude Code instructions for superfly/sprites-ex, covering sprites elixir sdk, quick reference, common commands, install dependencies and compile.
mitos CLAUDE.md
Instructions for mitos-run/mitos, covering claude.md, project overview, operating principles, commands and architecture.
tengu CLAUDE.md
Instructions for rfunix/tengu, covering claude.md — tengu mcp server, project overview, architecture, request flow and module map.