Paywary

Leaderboard / money-reactor.makar52nn2016.workers.dev / endpoint

POST https://money-reactor.makar52nn2016.workers.dev/api/ai-code-review

Scores measure reliability and honesty, not output quality.

72Cautionconfidence: medium
  • The payment wallet changed in the last 7 days, which caps the verdict at caution until it has been stable for a week.
  • The payment wallet changed 1 time in the last 30 days.
Category
Inference by llm, confidence 80%
Latest quote
$0.5 on Base to 0xF7f2…1baD
Uptime
100% / 7d, 100% / 30d
Delivery
none not yet paid-tested
Observed
none reported yet (opt-in wrapper telemetry)
HTTPS
yes
First listed
2026-11-16
Last probe
41m ago
Next probe
2026-11-18 11:49 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
50w 15%
Delivery after payment
n/aexcluded
Wallet stability
0w 10%
Listing age
7w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.10xC2B9…2130defaultyes2h ago

Paid probes

No paid probes yet. Paid probing is off by default and runs weekly per host under a strict spend cap; each paid probe links to its on-chain transaction here.

Delivery checks

Inside each paid probe we ask for something whose correct answer we know, then compare. A pass means the seller delivered what it was paid for; a fail means it charged and returned something wrong; inconclusive means we could not judge (no reference, unknown input shape, or a non-2xx response). Every row carries the request, the response hash and the reference so the verdict can be reproduced. Judged results feed the "Delivery after payment" component (pass 1, error after payment 0.25, fail 0); inconclusive rows are excluded; a fail in the last 14 days caps the verdict at caution. Methodology.

No delivery checks yet. They run inside the weekly paid probe.

Classification history

Every classification is kept; the newest row is the current category. Rules match the listing text; the model is consulted only when the rules are unsure.

WhenCategoryConfidenceMethodVersionEvidence
29h agoInference80%llmv1claude-haiku-5-5: The endpoint returns AI-generated code review output (bugs, security issues, style notes, verdict) produced by Llama/Qwen models, which is LLM model output rather than a deterministic web audit of a URL. Security review of supplied code is closest to inference, though web_audit and signal were considered and rejected because it audits submitted code, not a URL, and does not produce a trading or risk signal.
33h agoInference60%rulesv1rule inference matched "llama" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
41m agofree402100 msv2yes$0.50xF7f2…1baDprice_above_listingprice_mismatchpayto_mismatch
7h agofree40245 msv2yes$0.50xF7f2…1baDprice_above_listingprice_mismatchpayto_mismatch
13h agofree4021321 msv2yes$0.50xF7f2…1baDprice_above_listingprice_mismatchpayto_mismatch
20h agofree40231 msv2yes$0.50xF7f2…1baDprice_above_listingprice_mismatchpayto_mismatch
26h agofree402208 msv2yes$0.50xF7f2…1baDprice_above_listingprice_mismatchpayto_mismatch
32h agofree40250 msv2yes$0.50xF7f2…1baDprice_above_listingprice_mismatchpayto_mismatch
38h agofree402590 msv2yes$0.50xF7f2…1baDprice_above_listingprice_mismatchpayto_mismatch
45h agofree40222 msv2yes$0.50xF7f2…1baDprice_above_listingprice_mismatchpayto_mismatchpayto_changed
2d agofree40255 msv2yes$0.50x4Ce5…79C9price_above_listingprice_mismatchpayto_mismatch