Microsandbox is a runtime and library that runs untrusted workloads inside small virtual machines (microVMs), providing hardware-level isolation while supporting standard container images. It is for AI agents, user code, plugins, CI jobs, development environments, scrapers, and automation, and its catalogue instruction helps agents create and use these sandboxes.
Borrowing it
Nothing to install: this file belongs to superradcompany/microsandbox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/superradcompany/microsandbox/main/AGENTS.mdgit clone --depth 1 https://github.com/superradcompany/microsandboxWrote 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/superradcompany/microsandbox/agents-md)<a href="https://agentmods.dev/instructions/superradcompany/microsandbox/agents-md"><img src="https://agentmods.dev/badge/instructions/superradcompany/microsandbox/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/superradcompany/microsandbox/agents-md"><img src="https://agentmods.dev/badge/instructions/superradcompany/microsandbox/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.05656 | $0.05656 |
| Opus 5.5 | $0.02262 | $0.02262 |
| Sonnet 5.5 | $0.01131 | $0.01131 |
| Haiku 4.5 | $0.00566 | $0.00566 |
Grade A, and why
microsandbox 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 7d 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 — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
These instructions are only for agents contributing changes to this repository. Do not apply them to other repositories or to general agent behavior outside this contribution workflow.
Scope
- Follow these guidelines when editing code, docs, tests, examples, CI, or release files for microsandbox.
- Prefer repository conventions over generic agent habits. When unsure, inspect nearby files and match their style.
- Do not create branches, commit, push, tag, publish, or open pull requests unless the human explicitly asks.
- Check
git status --short --branchbefore making changes. Do not overwrite or revert user work unless explicitly asked.
Project Map
sdk/rustis the public Rust SDK crate.crates/clicontains themsbCLI.crates/runtimecontains VM runtime integration.crates/filesystem,crates/image,crates/network,crates/db,crates/migration,crates/metrics,crates/metrics-collector,crates/protocol, andcrates/utilsare shared internal crates.packages/agent-clientandpackages/microsandbox-typesare the shared agent-protocol client and wire-contract type packages, each with Rust and TypeScript implementations.crates/agentdis the in-guest agent. It is a workspace member; the musl guest binary that ships in releases is built separately.sdk/python,sdk/node-ts, andsdk/gocontain the language SDKs and native bindings.docs/contains the documentation site. Keep docs in sync with user-facing behavior.examples/contains runnable examples. Add new example projects only when requested or clearly required by the contribution.mcp/andskills/are submodules related to agent integrations.vendor/libkrunfwis a submodule for the kernel firmware library.
Repository layout:
.
|-- AGENTS.md
|-- Cargo.lock
|-- Cargo.toml
|-- COMPATIBILITY.md
|-- DEVELOPMENT.md
|-- Dockerfile.agentd
|-- justfile
|-- msb-entitlements.plist
|-- assets/
|-- crates/
| |-- agentd/
| |-- cli/
| |-- db/
| |-- filesystem/
| |-- image/
| |-- metrics/
| |-- metrics-collector/
| |-- migration/
| |-- network/
| |-- protocol/
| |-- runtime/
| |-- testing/
| | |-- init/
| | |-- macros/
| | `-- utils/
| `-- utils/
|-- docs/
| |-- changelog/
| |-- cli/
| |-- getting-started/
| |-- images/
| |-- networking/
| |-- observability/
| |-- recipes/
| |-- sandboxes/
| |-- sdk/
| `-- security/
|-- examples/
| |-- python/
| |-- rust/
| `-- typescript/
|-- mcp/
| |-- bin/
| |-- src/
| `-- package.json
|-- packages/
| |-- agent-client/
| `-- microsandbox-types/
|-- packaging/
| `-- docker/
|-- scripts/
| `-- smoke/
|-- sdk/
| |-- go/
| |-- node-ts/
| |-- rust/
| `-- python/
|-- skills/
| `-- microsandbox/
`-- vendor/
`-- libkrunfw/
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.
- 7d ago Changed · +6 lines · +126 tokens per session aa3d651fd706
- 21d ago Changed · +1 lines · +43 tokens per session ddccf2abd6cc
- 27d ago Changed · +8 lines · +321 tokens per session 4670e9eb3a12
- 29d ago Changed · +8 lines · +268 tokens per session 24ef8a810eca
- 1mo ago Changed · +23 lines · +532 tokens per session 223e8fca2509
- 1mo ago Changed · +2 lines · +10 tokens per session c534d4805653
- 1mo ago Changed · +4 lines · +221 tokens per session 593aaad96944
- 1mo ago Changed · +14 lines · +483 tokens per session c1e36b201eac
- 2mo ago First seen · 337 lines · 3,652 tokens per session scan A c8ade3155e3a
microsandbox AGENTS.md is an instructions file published in the GitHub repository superradcompany/microsandbox (8,956 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,656 tokens to every session, about $0.0226 per session on Opus 5.5. 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.
microsandbox AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| microsandbox AGENTS.mdsuperradcompany/microsandbox | Instructions file | 9.0k | yesterday | Apache-2.0 | A | 5,656 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |