Help us improve
Share bugs, ideas, or general feedback.
From alchemy-skills
Verifies AI agent reasoning before executing trades or autonomous actions via adversarial multi-model critique (Claude, Grok, DeepSeek). Returns ALLOW, BLOCK, or UNCERTAIN verdict with confidence score.
npx claudepluginhub moonpay/skills --plugin moonpay-skillsHow this skill is triggered — by the user, by Claude, or both
Slash command
/alchemy-skills:thoughtproof-reasoning-checkThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Before executing a trade or autonomous action, verify that the agent's reasoning is sound. ThoughtProof runs adversarial multi-model critique and returns a signed verdict: ALLOW, BLOCK, or UNCERTAIN.
Checks trust scores and verdicts for agents/tokens on Base using Maiat's indexed database. Use before swaps, transfers, or agent interactions to avoid scams.
Reviews prediction-market, basket, oracle, and trading-agent workflows for compliance, safety, data-quality, privacy, and execution risk before handling venue auth, portfolio data, or trade planning.
Orchestrates Claude + Gemini CLI + Codex CLI for 3-stage multi-AI consensus (opinions → rebuttals → synthesis) on code reviews, market analysis, investments, risks. Auto-detects domain.
Share bugs, ideas, or general feedback.
Before executing a trade or autonomous action, verify that the agent's reasoning is sound. ThoughtProof runs adversarial multi-model critique and returns a signed verdict: ALLOW, BLOCK, or UNCERTAIN.
mp wallet createCheck reasoning quality before a trade:
curl -X POST https://api.thoughtproof.ai/v1/check \
-H "Content-Type: application/json" \
-d '{"claim": "Swap $2K USDC to ETH. ETH at $2180, 6% below 30d MA, RSI 34.", "stakeLevel": "medium", "domain": "financial"}'
First call returns 402 with x402 payment details (amount, recipient, asset on Base). Pay, then retry the same request to receive the verdict.
{
"verdict": "ALLOW",
"confidence": 0.82,
"objections": [],
"durationMs": 55000
}
| Verdict | Meaning | Action |
|---|---|---|
ALLOW | Reasoning passed verification | Proceed |
BLOCK | Material reasoning defects or unacceptable risk | Do not execute |
UNCERTAIN | Safe escalation state — insufficient clean evidence to justify ALLOW or BLOCK | Gather more context or require review |
ThoughtProof pricing is stake-based.
| Stake Level | Standard | Lite | Use case |
|---|---|---|---|
low | $0.01 | $0.005 | Routine low-value actions |
medium | $0.02 | $0.01 | Standard trades and service payments |
high | $0.05 | — | Large or sensitive actions |
critical | $0.10 | — | High-value or highly risky actions |
Notes:
lite is only available for low and medium stake.high and critical always execute on the standard tier.MoonPay handles the payment execution. ThoughtProof verifies whether the decision to pay is well-reasoned before settlement.
Example:
moonpay-swap-tokens, the agent sends the reasoning to ThoughtProof.ALLOW → proceed with swapBLOCK → stop, surface objectionsUNCERTAIN → escalate, ask for clarification or reviewExample failure:
BLOCKExample pass:
ALLOWThis gives the agent stack two layers: