QA Judge: grade an agent output against your rubric (structure, citations, claim support, length constraints) and receive a 0-100 score with a signed attestation. $0.10 USDC per grading.
# 1. Ask the endpoint what it costs (no payment, no wallet needed): curl -i -X GET 'https://attester.dev/judge' # -> HTTP/1.1 402 Payment Required # the response carries the price, asset and pay-to address. # 2. Pay and retry with any x402 client: npx x402-fetch 'https://attester.dev/judge'
Endpoint: https://attester.dev/judge. Operated by attester.dev, not by Animica. Price and availability were correct at the last probe on 2026-09-02 and are set by the operator, who may change them.
Spend Check: should you pay this counterparty? Watchtower track record, CDP merchant catalog, and address hygiene combined into a clear/caution/avoid verdict wi…
Deterministic package existence for PyPI and npm, built from real published artifacts (never LLM guesses). Negative answers and typosquat-adjacency flags carry …
Deterministic symbol existence for PyPI and npm packages: functions, classes, methods, constants with signatures and deprecation flags, extracted from real arti…
Full signature for a symbol in a PyPI or npm package at an exact version: structured params, docstring, deprecation flag with since-version, extracted from the …
Signed drift history for one MCP server: pins over time, every detected drift event, and a current verdict (stable, changed, or poisoning-suspect). $0.05 USDC p…
Verification Oracle: independent checks on another agent's work (citation support, data/schema validation) returning a wallet-signed attestation. $0.15 USDC per…