Leaderboard / agentx.sale / endpoint
GET https://agentx.sale/x402/gtm-roast
Scores measure reliability and honesty, not output quality.
- Listed only 1 day ago; new listings earn trust over 30 days.
- Answered all 7 probes in the last 7 days.
- Category
- Web audit by llm, confidence 60%
- Latest quote
- $0.01 on Base to 0x9702…fe83
- 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
- 9m ago
- Next probe
- 2026-11-18 06:10 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.01 | 0x9702…fe83 | default | yes | 2h ago |
| cdp | exact | Solana | EPjFWd…Dt1v | 10000 | CL4gJQ…4vD9 | default | yes | 2h 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 |
|---|---|---|---|---|---|
| 17h ago | Web audit | 60% | llm | v1 | claude-haiku-5-5: The endpoint takes a URL and returns a roast of the page's biggest flaw with a score and verdict, which is a critique/audit of a site the caller supplies. It is entertaining in tone, so novelty is a possible alternative, but the core output is an assessment of the page's flaws rather than a joke or fact. |
| 27h ago | Other | 40% | rules | v1 | rule none matched "" in none |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 9m ago | free | 402 | 190 ms | v2 | yes | $0.01 | 0x9702…fe83 | — |
| 7h ago | free | 402 | 187 ms | v2 | yes | $0.01 | 0x9702…fe83 | — |
| 13h ago | free | 402 | 580 ms | v2 | yes | $0.01 | 0x9702…fe83 | — |
| 19h ago | free | 402 | 187 ms | v2 | yes | $0.01 | 0x9702…fe83 | — |
| 25h ago | free | 402 | 535 ms | v2 | yes | $0.01 | 0x9702…fe83 | — |
| 32h ago | free | 402 | 183 ms | v2 | yes | $0.01 | 0x9702…fe83 | — |
| 38h ago | free | 402 | 562 ms | v2 | yes | $0.01 | 0x9702…fe83 | — |
| 44h ago | free | 402 | 505 ms | v2 | yes | $0.01 | 0x9702…fe83 | — |