SmolVM AGENTS.md

SmolVM AGENTS.md is an instructions file for Codex, OpenCode from CelestoAI/SmolVM. It costs 1,260 tokens per session, scanned A, original, Apache-2.0.

Development and release guidance for SmolVM, a system that gives AI agents disposable virtual computers for running code and commands safely.

In plain words
What is it for?
Use it when running tests or formatting, changing guest agents or images, updating release pins, and preparing a SmolVM package release.
Why use it?
It provides the checks needed to test changes and keep published virtual-machine images tied to the correct release versions and checksums.

Instructions file for CodexOpenCode

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/celestoai/smolvm/agents-md
Clone the repo
git clone --depth 1 https://github.com/CelestoAI/SmolVM

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 SmolVM AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/celestoai/smolvm/agents-md.svg)](https://agentmods.dev/instructions/celestoai/smolvm/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/celestoai/smolvm/agents-md"><img src="https://agentmods.dev/badge/instructions/celestoai/smolvm/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,260 This file is loaded in full into every session.
When invoked 1,260 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 $0.01260 $0.01260
Opus 5 $0.00630 $0.00630
Sonnet 5 $0.00252 $0.00252
Haiku 4.5 $0.00126 $0.00126

Measured 4d ago against content hash 94f684f422e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SmolVM 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 · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SmolVM Context

SmolVM gives AI agents their own disposable computer. Each sandbox is a lightweight virtual machine that boots in seconds, runs any code or command you throw at it, and disappears when you're done — nothing touches the host.

🚀 Project Overview

SmolVM is specifically designed to provide a secure "sandbox" for AI agents to execute code, browse the web, or perform system-level tasks safely.

🧪 Development

Key Commands

  • Testing: pytest (runs the suite in tests/)
  • Linting & Formatting: uv run ruff check . or uv run ruff format .

Release checklist

  • For guest-agent or published-image changes, build and smoke the new image release before tagging the SmolVM package release.
  • Update src/smolvm/images/published.py with the new IMAGES_RELEASE_TAG and rootfs SHA pins before the PyPI tag is pushed.
  • Also update src/smolvm/images/builder.py::_GUEST_AGENT_RELEASE_SHA256 from the smolvm-guest-agent-linux-<arch>.sha256 release assets. This is a separate pin from the rootfs manifest.
  • Verify both paths: uv run smolvm ... from a source checkout may build or use the local guest-agent binary, while smolvm ... from uv tool uses the installed wheel and downloads the standalone guest-agent release binary.
  • Only tag the SmolVM package release after the image manifest, guest-agent binary SHA pins, image smoke, and focused tests are complete.

CLI design

  • New CLI commands follow a NOUN-VERB structure: smolvm <noun> <verb>, e.g. smolvm codex start, not smolvm start codex.
  • The noun names the resource (a sandbox, a harness, a browser session); the verb names the action on it (start, stop, ssh).
  • This scales naturally as actions grow: smolvm codex start, then later smolvm codex logs, smolvm codex status, etc.
  • When adding a new harness or resource, register it as a top-level subcommand and put its actions underneath, instead of overloading a global verb.
  • Documented exceptions: the top-level smolvm prune and smolvm images aliases exist for muscle memory (images mirrors docker images); both delegate to their NOUN-VERB homes (image prune, image list). Do not add further top-level aliases without discussion.
  • smolvm completion <shell> is an accepted top-level meta-command (like git/gh completion): it acts on the CLI itself rather than a sandbox resource, so it sits outside the NOUN-VERB rule by design.

Read the full file on GitHub · 114 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 First seen · 114 lines · 1,260 tokens per session scan A 94f684f422e8

Subscribe to this mod's changes

SmolVM AGENTS.md is an instructions file published in the GitHub repository CelestoAI/SmolVM (866 stars, last pushed 7d ago), licensed Apache-2.0. It adds 1,260 tokens to every session, about $0.0063 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.