Leaderboard / agent402.tools / endpoint
POST https://agent402.tools/api/loop-gate
Scores measure reliability and honesty, not output quality.
- Listed only 3 days ago; new listings earn trust over 30 days.
- Answered all 13 probes in the last 7 days.
- Category
- Signal by llm, confidence 60%
- Latest quote
- $0.001 on Base to 0xaBF4…a9D0
- 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
- 3h ago
- Next probe
- 2026-11-19 14:39 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | eip155:5042 | 0x3600…0000 | 1000 | 0xaBF4…a9D0 | default | yes | 5h ago |
| cdp | exact | eip155:143 | 0x7547…b603 | 1000 | 0xaBF4…a9D0 | default | yes | 5h ago |
| cdp | exact | Base | 0x8335…2913 | $0.001 | 0xaBF4…a9D0 | default | yes | 5h ago |
| cdp | exact | Arbitrum | 0xaf88…5831 | 1000 | 0xaBF4…a9D0 | default | yes | 5h ago |
| cdp | exact | algorand:wGHE2Pwdvd7S12BL5FaOP20EGYesN73k | 31566704 | 1000 | C7IIHG…2XIE | default | yes | 5h ago |
| cdp | exact | Solana | EPjFWd…Dt1v | 1000 | J7aN3P…3xwg | default | yes | 5h ago |
| cdp | exact | eip155:4663 | 0x5fc5…d168 | 10000 | 0xaBF4…a9D0 | default | yes | 5h ago |
| cdp | exact | Polygon | 0x3c49…3359 | 1000 | 0xaBF4…a9D0 | default | yes | 5h ago |
| cdp | exact | eip155:1329 | 0xe15f…2392 | 1000 | 0xaBF4…a9D0 | default | yes | 5h ago |
| cdp | upto | Base | 0x8335…2913 | $0.001 | 0xaBF4…a9D0 | permit2 | yes | 5h ago |
| cdp | exact | stellar:pubnet | CCW67T…MI75 | 10000 | GDNJXC…WWRL | default | yes | 5h ago |
| payai | exact | Solana | EPjFWd…Dt1v | 1000 | J7aN3P…3xwg | default | yes | 5h ago |
| cdp | exact | Avalanche | 0xB97E…8a6E | 1000 | 0xaBF4…a9D0 | default | yes | 5h ago |
| cdp | exact | eip155:10 | 0x0b2C…Ff85 | 2000 | 0xaBF4…a9D0 | default | yes | 5h ago |
| cdp | exact | eip155:42220 | 0xcebA…118C | 1000 | 0xaBF4…a9D0 | default | yes | 5h ago |
| cdp | exact | eip155:57073 | 0x2D27…EAEd | 1000 | 0xaBF4…a9D0 | default | yes | 5h ago |
| payai | exact | Base | 0x8335…2913 | $0.001 | 0xaBF4…a9D0 | default | yes | 5h ago |
Listing changes
| When | Event | From | To |
|---|---|---|---|
| 39h ago | disappeared | — | — |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
| 40h ago | price_changed | 5000 | 10000 |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
| 40h ago | description_changed | Should the loop run another iteration? Send the goal, the iteration that just finished (lastOutput, iteration), and optionally maxIterations, a budget { spentUsd, maxUsd }, the history of earlier iterations (up to 20 of { iteration, summary }, oldest first) and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks that produced it (goalMet, budgetExceeded, iterationsExhausted, repeating, stuck, constraintBreached) and nextStep (iterate. | Should an agent loop run another iteration? Send the goal, the last output and its iteration, plus optional maxIterations, budget, history and constraints; get back decision (continue, stop or escalate), reason, confidence (0 to 1), the checks behind it and a next step. Budget and iteration limits are checked in code first, with no model call; otherwise a judgment model answers. Use it between iterations. |
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 |
|---|---|---|---|---|---|
| 39h ago | Signal | 60% | llm | v1 | claude-haiku-5-5: The endpoint returns a continue/stop/escalate decision with confidence and reasoning about whether an agent loop should run again, which fits an AI-enriched judgment verdict best. It is not a pure inference endpoint because its output is a decision rather than generated text, and it is not a risk forecast, so confidence is moderate. |
| 39h ago | Other | 40% | rules | v1 | rule none matched "" in none |
| 45h ago | Signal | 60% | llm | v1 | claude-haiku-5-5: The endpoint returns a judgment verdict (continue, stop or escalate) with confidence and checks, which is closest to a decision or risk verdict in the signal category. It is an agent-loop control judgment rather than a market signal, so confidence is moderate, and the category could arguably be inference given its AI-driven nature. |
| 3d ago | Other | 40% | rules | v1 | rule none matched "" in none |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 3h ago | free | 402 | 38 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |
| 9h ago | free | 402 | 32 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |
| 15h ago | free | 402 | 257 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |
| 22h ago | free | 402 | 37 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |
| 28h ago | free | 402 | 63 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |
| 35h ago | free | 402 | 566 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |
| 41h ago | free | 402 | 428 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |
| 2d ago | free | 402 | 426 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |
| 2d ago | free | 402 | 120 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |
| 3d ago | free | 402 | 49 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |
| 3d ago | free | 402 | 96 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |
| 3d ago | free | 402 | 86 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |
| 3d ago | free | 402 | 78 ms | v2 | yes | $0.001 | 0xaBF4…a9D0 | — |