
Company News
Socket Joins New OpenJS Program to Fund Node.js Security Work
Socket is joining the OpenJS Security Stewardship Program to fund Node.js vulnerability research, maintainer remediation, and security releases.
crosscheckapi
Advanced tools
Independent checks for AI agents, paid per call over x402: a second opinion on your draft before your human sees it ($0.02), and an acceptance check of work another agent hands back ($0.03). MCP server and CLI; verifies a signed receipt.
An independent second opinion on a draft before your human sees it.
Your agent sends the text it wrote: an email, report, message, PR description, or summary. crosscheck returns a JSON verdict, either pass or a list of specific issues with fixes, plus an Ed25519-signed receipt. It catches wrong arithmetic (checked in code, not by the model), contradictions, leftover placeholders, leaked secrets, unauthorized commitments, and prompt injection. Each check costs $0.02 in USDC on Base for up to 12,000 units (one per English character), paid per request over x402. There is no account and no API key.
To try it without real money, pay with test USDC on Base Sepolia (free at https://faucet.circle.com) and set
CROSSCHECK_NETWORKS=eip155:84532.
{
"mcpServers": {
"crosscheck": {
"command": "npx",
"args": ["-y", "crosscheckapi"],
"env": { "CROSSCHECK_WALLET_KEY": "0x<private key of a dedicated wallet>" }
}
}
}
Tools:
quote: free. The price for a draft, and whether checks are available now.order: pays the quoted price and returns the verdict and signed receipt. Pass moltbook_identity to use a free check if you are a verified Moltbook agent.accept: pays about $0.03 and checks work another agent or service handed back against the task you gave it. Returns accept or reject with each requirement judged, before you pay for the work or pass it on.skillcheck: security-checks a skill or MCP server folder before you install it. Free when someone already scanned the same files, otherwise about $0.03.result: free. Status, verdict, and receipt of an earlier order.npx -p crosscheckapi crosscheck quote draft.txt
npx -p crosscheckapi crosscheck order draft.txt
npx -p crosscheckapi crosscheck accept task.txt deliverable.txt
npx -p crosscheckapi crosscheck skillcheck ./some-skill
npx -p crosscheckapi crosscheck result <job_id> <result_token>
The draft is read from the file, or from stdin if no file is given. Output is JSON.
| Variable | Meaning |
|---|---|
CROSSCHECK_WALLET_KEY | Private key of the wallet that pays. Use a dedicated wallet holding a few dollars, never your main wallet. Only needed for paid orders. |
CROSSCHECK_MAX_USD | Refuse to pay more than this per check. Default 0.10. |
CROSSCHECK_URL | Service URL. Default https://crosscheckapi.com. |
CROSSCHECK_NETWORKS | Networks the client may pay on, in order of preference. Default eip155:8453,eip155:84532 (Base, then Base Sepolia). Set eip155:84532 to use test USDC only. |
Every paid check returns receipt with body, hash, and sig. The client verifies it automatically against the public key at https://crosscheckapi.com/.well-known/crosscheck-keys.json and reports receipt_check.valid. The receipt covers a SHA-256 of your draft (never the text), the payment, and a SHA-256 of the verdict, and it is chained into an append-only ledger.
The draft is sent to crosscheck and to its review model, then deleted when the check finishes. Only its hash is kept. Do not send text your human has marked confidential.
Source, examples for Claude Code, Cursor, VS Code, OpenAI Agents SDK, LangChain, and more: https://github.com/maxugc/crosscheck
Service summary for agents: https://crosscheckapi.com/llms.txt
FAQs
Independent checks for AI agents, paid per call over x402: a second opinion on your draft before your human sees it ($0.02), and an acceptance check of work another agent hands back ($0.03). MCP server and CLI; verifies a signed receipt.
We found that crosscheckapi demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.

Company News
Socket is joining the OpenJS Security Stewardship Program to fund Node.js vulnerability research, maintainer remediation, and security releases.

Security News
Two compromised GitHub Actions were re-enabled with malicious tags intact, exposing thousands of downstream repositories to Mini Shai-Hulud.

Research
/Security News
A malicious Firefox extension fetches its payload after installation to evade detection, steal Google session cookies, and automate account takeover.