Leaderboard / agent-data-tools.revmesh2074.workers.dev / endpoint
GET https://agent-data-tools.revmesh2074.workers.dev/github/releases
Scores measure reliability and honesty, not output quality.
- Listed only 2 days ago; new listings earn trust over 30 days.
- Answered all 11 probes in the last 7 days.
- Category
- Web scrape by llm, confidence 60%
- Latest quote
- $0.002 on Base to 0x6293…f800
- 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
- 46m ago
- Next probe
- 2026-11-19 01:59 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Solana | EPjFWd…Dt1v | 2000 | 82wfSC…a9Q6 | default | yes | 3h ago |
| cdp | exact | Base | 0x8335…2913 | $0.002 | 0x6293…f800 | default | yes | 3h ago |
| cdp | exact | Polygon | 0x3c49…3359 | 2000 | 0x6293…f800 | default | yes | 3h ago |
| cdp | exact | Arbitrum | 0xaf88…5831 | 2000 | 0x6293…f800 | default | yes | 3h 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.
| When | Category | Confidence | Method | Version | Evidence |
|---|---|---|---|---|---|
| 31h ago | Web scrape | 60% | llm | v1 | claude-haiku-5-5: Returns release listings and release-note text for a public GitHub repository, which is closest to fetching and reading page content, though it is structured release metadata rather than a generic page scrape. No better category fits cleanly. |
| 47h ago | Public data | 60% | rules | v1 | rule public_data matched "github release" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 46m ago | free | 402 | 196 ms | v2 | yes | $0.002 | 0x6293…f800 | — |
| 8h ago | free | 402 | 402 ms | v2 | yes | $0.002 | 0x6293…f800 | — |
| 14h ago | free | 402 | 20 ms | v2 | yes | $0.002 | 0x6293…f800 | — |
| 21h ago | free | 402 | 29 ms | v2 | yes | $0.002 | 0x6293…f800 | — |
| 27h ago | free | 402 | 87 ms | v2 | yes | $0.002 | 0x6293…f800 | — |
| 34h ago | free | 402 | 43 ms | v2 | yes | $0.002 | 0x6293…f800 | — |
| 40h ago | free | 402 | 37 ms | v2 | yes | $0.002 | 0x6293…f800 | — |
| 46h ago | free | 402 | 29 ms | v2 | yes | $0.002 | 0x6293…f800 | — |
| 2d ago | free | 402 | 138 ms | v2 | yes | $0.002 | 0x6293…f800 | — |
| 2d ago | free | 402 | 67 ms | v2 | yes | $0.002 | 0x6293…f800 | — |
| 3d ago | free | 402 | 36 ms | v2 | yes | $0.002 | 0x6293…f800 | — |