Paywary

Leaderboard / saferead.grindfree.net / endpoint

GET https://saferead.grindfree.net/v1/read

Scores measure reliability and honesty, not output quality.

94Payconfidence: medium
  • Listed only 0 days ago; new listings earn trust over 30 days.
  • Answered all 4 probes in the last 7 days.
Category
Web audit by rules, confidence 90%
Latest quote
$0.002 on Base to 0xe4b5…721b
Uptime
100% / 7d, 100% / 30d
Delivery
none not yet paid-tested
HTTPS
yes
First listed
2026-11-16
Last probe
4h ago
Next probe
2026-11-17 22:41 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
100w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
3w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.0020xe4b5…721bdefaultyes2h ago

Listing changes

WhenEventFromTo
7h agodescription_changedRead clean: safe web page reader for AI agents. Fetches a URL (SSRF-guarded) and returns clean Markdown or text with hidden content and prompt injections removed or flagged — hidden HTML (display:none, font-size:0, off-screen), comments, invisible Unicode, and agent-directed instructions — plus title, removed/flagged segments, an allow|warn|block verdict and fetch metadata. HTML, text, Markdown, JSON, PDF. GET ?url=<page URL> works too.Read a web page as clean Markdown for AI (read clean). Use when your agent fetches a URL it did not write: returns LLM-ready Markdown with hidden HTML, comments, invisible Unicode and prompt injections removed or flagged, plus title, allow|warn|block verdict and fetch metadata. Honours robots.txt. Only successful reads are charged. Search intents: url to markdown, web page to markdown, read url. GET ?url=<page URL> works too.

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
7h agoWeb audit90%rulesv1rule web_audit matched "prompt injection" in description
23h agoWeb audit90%rulesv1rule web_audit matched "prompt injection" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
4h agofree402376 msv2yes$0.0020xe4b5…721b—
11h agofree402305 msv2yes$0.0020xe4b5…721b—
17h agofree402322 msv2yes$0.0020xe4b5…721b—
23h agofree402687 msv2yes$0.0020xe4b5…721b—