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 skills/rivet-dev/agentos/sanity-checknpx skills add rivet-dev/agentos --skill sanity-checkgit clone --depth 1 https://github.com/rivet-dev/agentosWhat 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 | $0.00037 | $0.01249 |
| Opus 5 | $0.00018 | $0.00624 |
| Sonnet 5 | $0.00007 | $0.00250 |
| Haiku 4.5 | $0.00004 | $0.00125 |
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 3d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sanity Check
This is a P6/full-validation check. It installs from npm in a fresh project, boots an AgentOS VM, spawns a Pi agent session, writes a file, reads it back, and verifies the contents.
Usage
/sanity-check— run in a temp directory on the host/sanity-check docker— run inside anode:22Docker container/sanity-check <custom instructions>— extra instructions, such as "use rc.3", "use pnpm", or "test on node 20"
What it tests
npm installof@rivet-dev/agentos-core,@rivet-dev/agentos-pi,@agentos-software/commonfrom the public npm registry- Boot a VM with WASM coreutils (bash, cat, sh, etc.) and the Pi SDK ACP adapter
- Create a Pi agent session with a real Anthropic API key
- Send a prompt that uses the write tool to create
/tmp/test.txtwith "Hello from Agent OS!" and the bash tool to runcat /tmp/test.txt - Verify the file contents from the host side via
vm.readFile()
Requirements
ANTHROPIC_API_KEYmust be set in the environment. If not set, load it from~/misc/env.txt.- Node.js 22+ (or Docker with
node:22image)
Steps
1. Set up the test project
Create a temp directory (e.g. /tmp/agentos-sanity-XXXX) with two files:
package.json:
{
"name": "agentos-sanity-check",
"private": true,
"type": "module",
"dependencies": {
"@rivet-dev/agentos-core": "*",
"@rivet-dev/agentos-pi": "*",
"@agentos-software/common": "*",
"@mariozechner/pi-coding-agent": "^0.60.0",
"@agentclientprotocol/sdk": "^0.16.1"
}
}
If the user specifies a version (e.g. "use rc.3"), pin @rivet-dev/agentos-core and @rivet-dev/agentos-pi to that version.
test.mjs:
import { AgentOs } from "@rivet-dev/agentos-core";
import common from "@agentos-software/common";
import pi from "@rivet-dev/agentos-pi";
const ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY;
if (!ANTHROPIC_API_KEY) {
console.error("ANTHROPIC_API_KEY is required");
process.exit(1);
}
console.log("Creating VM with common + pi...");
const vm = await AgentOs.create({ software: [common, pi] });
console.log("Creating PI agent session...");
const { sessionId } = await vm.createSession("pi", {
env: { ANTHROPIC_API_KEY },
});
console.log(`Session created: ${sessionId}`);
vm.onSessionEvent(sessionId, (event) => {
const params = event.params;
if (params?.update?.sessionUpdate === "agent_message_chunk") {
process.stdout.write(params.update.content?.text ?? "");
}
});
console.log("\nSending prompt...");
const response = await vm.prompt(
sessionId,
'Write the text "Hello from Agent OS!" to /tmp/test.txt using the write tool. Then use the bash tool to run `cat /tmp/test.txt` and tell me what it says.',
);
console.log(`\n\nPrompt completed: ${response.stopReason}`);
console.log("\nVerifying file...");
try {
const data = await vm.readFile("/tmp/test.txt");
const text = new TextDecoder().decode(data);
console.log(`File contents: "${text.trim()}"`);
if (text.includes("Hello from Agent OS!")) {
console.log("\n✅ E2E TEST PASSED");
} else {
console.log("\n❌ E2E TEST FAILED: wrong content");
process.exit(1);
}
} catch (err) {
console.log(`\n❌ E2E TEST FAILED: ${err.message}`);
process.exit(1);
}
vm.closeSession(sessionId);
await vm.dispose();
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.
- 3d ago First seen · 143 lines · 37 tokens per session scan A 3c0957296e8c
sanity-check is a skill published in the GitHub repository rivet-dev/agentos (4,444 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 1,249 once invoked, about $0.0002 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 skills, from other repositories
test-pyramid
Analyze the repo's unit and E2E tests and propose rebalancing toward a test pyramid — which E2E tests (or assertions inside them) can be covered by unit tests, which unit-level gaps genuinely need E2E coverage, and where coverage is duplicated. Use when the user asks about test pyramid, test rebalancing, "should this…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
smoke-test
End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…
maintain-model-list
Maintain the supported LLM model list: add a new model, or run routine maintenance to verify availability and discover new models worth adding. Use when the user asks to add/support a model, update the model list, or check model availability.
update-changelog
Update docs/CHANGELOG.md from git history, GitHub releases, and code diffs. Use when: writing release notes, syncing the latest changelog entry, summarizing a new tag, or keeping changelog wording concise and consistent.
git-cleanup
Clean up local git branches and remotes accumulated from PR reviews. Use when the user asks to clean branches, remove stale remotes, or tidy up the local git state.