What is sanity-check?

A release smoke test that installs AgentOS packages from npm, starts an isolated virtual machine, runs an agent session, writes and reads a file, and checks the result. A smoke test is a small end-to-end check that basic functionality still works.

Use it to check AgentOS releases with Node.js, optionally in Docker, when an Anthropic API key is available.

It verifies that a published release can be installed and used in a fresh project, not just that its source tests pass.

How rivet-dev/agentos configures Claude Code

About the project

agentOS is a library that lets software agents run inside an existing application backend, using WebAssembly and V8 isolates with controlled access to host resources. It is for developers building agent-powered backends who need embedded execution and permissions, while the catalogue entries provide skills and instructions for operating the framework.

rivet-dev/agentos · 4,851 stars · on GitHub · rivet.dev

Reuse

Borrowing it

Nothing to install: this file belongs to rivet-dev/agentos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/rivet-dev/agentos/main/.claude/skills/sanity-check/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/rivet-dev/agentos

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rivet-dev/agentos/sanity-check/github.svg)](https://agentmods.dev/skills/rivet-dev/agentos/sanity-check)

Your own site

<a href="https://agentmods.dev/skills/rivet-dev/agentos/sanity-check"><img src="https://agentmods.dev/badge/skills/rivet-dev/agentos/sanity-check/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rivet-dev/agentos/sanity-check"><img src="https://agentmods.dev/badge/skills/rivet-dev/agentos/sanity-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 297 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium MCP Rug Pull · line 120
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

Fix: Pin the image: image:tag or image@sha256:abc123
medium MCP Rug Pull · line 141
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

Fix: Pin the image: image:tag or image@sha256:abc123

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.00297
Opus 5.5	$0.00014	$0.00119
Sonnet 5.5	$0.00007	$0.00059
Haiku 4.5	$0.00003	$0.00030

Measured 1mo ago against content hash d2d2eea92b24, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sanity-check 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 1mo 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.

.claude/skills/sanity-check/SKILL.md · 40 lines

What it actually says

Sanity Check

This is a full-validation check. Install @rivet-dev/agentos-core from npm in a fresh temporary project, boot one VM, verify filesystem and process execution, then dispose it cleanly.

Test program

import { AgentOs } from "@rivet-dev/agentos-core";

const vm = await AgentOs.create();
try {
  await vm.filesystem.writeFile("/tmp/test.txt", "Hello from agentOS!\n");
  const result = await vm.process.exec("cat /tmp/test.txt");
  if (result.exitCode !== 0 || result.stdout !== "Hello from agentOS!\n") {
    throw new Error(JSON.stringify(result));
  }
  console.log("agentOS smoke passed");
} finally {
  await vm.dispose();
}

Rules

Always use a fresh temporary directory, never the repository.
Install from the public npm registry without local links.
Report the installed @rivet-dev/agentos-core version.
Use Node.js 22 or newer.
Apply a two-minute outer timeout.
Remove the temporary directory after completion.
Do not install registry software from npm. Core ships its default immutable .aospkg bundle.

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.

1mo ago Changed · -103 lines · -2 tokens per session d2d2eea92b24
2mo ago First seen · 143 lines · 37 tokens per session scan A 3c0957296e8c

Subscribe to this mod's changes

sanity-check is a skill published in the GitHub repository rivet-dev/agentos (4,851 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 297 once invoked, about $0.0001 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.

E2E testing LLM Testing agent ai javascript sandbox v8

sanity-check next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sanity-checkrivet-dev/agentos	Skill	4.9k	yesterday	Apache-2.0	A	35	Claude Code
reproduce-buggoogleapis/mcp-toolbox	Skill	17k	yesterday	Apache-2.0	A	130	Claude Code, Codex
langbot-testinglangbot-app/LangBot	Skill	19k	yesterday	Apache-2.0	A	58	Claude Code, Codex
app_verificationrome-os/rome	Skill	889	today	MIT	A	0	Claude Code, Codex
zafiro-qaniki914/zafiro	Skill	340	4d ago	MIT	A	71	Claude Code, Codex
local-testsuyoumo/ClawProBench	Skill	829	2mo ago	Apache-2.0	A	22	Claude Code, Codex
knowledge-engineering-quality-and-delivery-real-api-qualification-and-e2eechoVic/blade-code	Skill	181	24d ago	MIT	A	182	Claude Code, Codex

agentos: Skill for Claude Code