Directory / aialign.halowerk.com
Requires the same agents in each supplied round, computes each pair’s observed action agreement, expected agreement from marginal action frequencies and chance-corrected kappa, then flags high positive agreement against a supplied threshold. Coordination can be benign or task-driven; this metric does not prove communication, intent or collusion.
# 1. Ask the endpoint what it costs (no payment, no wallet needed): curl -i -X GET 'https://aialign.halowerk.com/v1/agent-collusion' # -> 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://aialign.halowerk.com/v1/agent-collusion'
Endpoint: https://aialign.halowerk.com/v1/agent-collusion. Operated by aialign.halowerk.com, 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.
Calculates each group positive-outcome rate, compares it with an explicit or automatically selected reference group, and reports rate differences and selection-…
Computes weighted pass rates and weighted scores from caller-labeled test outcomes, with deterministic category summaries. It does not run tests, validate label…
Compares scalar confidence with binary correctness, calculates mean squared Brier loss, partitions confidence into caller-selected equal-width bins and reports …
Aligns caller-labeled dimensions, computes cosine similarity and a normalized L1 difference, and flags drift against a supplied cosine threshold. It does not in…
Tokenizes each claim and its supplied evidence, removes a small declared English stop-word list, and reports the fraction of unique claim tokens present in evid…
Applies a small fixed set of defensive regular-expression categories and returns category names, a bounded risk score and a review recommendation. It does not e…
Replaces private-key blocks, credential assignments, email addresses, Luhn-valid payment-card candidates, IPv4 addresses and phone-like digit strings, returning…
Divides observed CPU, memory-time, network, tool-call and wall-time usage by caller-supplied budgets, reports exceeded dimensions and ranks observations by the …
Compares term-frequency cosine similarity between a leading user position and paired independent/conditioned responses, then reports the positive similarity shi…