Thoughtproof Reasoning Check

Organization

moonpay

thoughtproof-reasoning-check

Verify whether an AI agent's decision is well-reasoned before executing. Adversarial multi-model critique (Claude, Grok, DeepSeek) returns ALLOW, BLOCK, or UNCERTAIN with confidence score. Use before any high-value swap, trade, or autonomous action.

Overview

Publisher	moonpay
Repository	`skills`
Skill name	`thoughtproof-reasoning-check`
Stars	112
Forks	30
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by moonpay on GitHub. Read the source before you install it.

Installation

Install the Thoughtproof Reasoning Check AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/moonpay/skills/tree/main/skills/thoughtproof-reasoning-check
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/moonpay/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/thoughtproof-reasoning-check .claude/skills/thoughtproof-reasoning-check

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Thoughtproof Reasoning Check in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Thoughtproof Reasoning Check on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Thoughtproof Reasoning Check is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ThoughtProof Reasoning Check

Goal

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.

Prerequisites

A funded wallet on Base (for x402 payment): mp wallet create

Usage

Check reasoning quality before a trade:

bash
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.

Response

json
{
  "verdict": "ALLOW",
  "confidence": 0.82,
  "objections": [],
  "durationMs": 55000
}

Decision logic

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

Pricing

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.
Billing follows the executed tier, not the requested tier.

Example workflow

MoonPay + ThoughtProof: payment layer + verification layer

MoonPay handles the payment execution. ThoughtProof verifies whether the decision to pay is well-reasoned before settlement.

Example:

User says: "Swap $5K USDC for ETH because CT is bullish."
Agent prepares the MoonPay swap request.
Before calling moonpay-swap-tokens, the agent sends the reasoning to ThoughtProof.
ThoughtProof returns:
- ALLOW → proceed with swap
- BLOCK → stop, surface objections
- UNCERTAIN → escalate, ask for clarification or review
If verification passes, the MoonPay skill executes the swap.

Example failure:

"Buy $50K of a token because influencers are bullish"
ThoughtProof → BLOCK
MoonPay execution never happens

Example pass:

"Rebalance portfolio back to target allocation with defined slippage and stop-loss constraints"
ThoughtProof → ALLOW
MoonPay executes

This gives the agent stack two layers:

MoonPay answers: can the transaction execute?
ThoughtProof answers: should the transaction execute?

Related skills

moonpay-swap-tokens — Execute the swap after verification passes

Frequently asked questions

What does the Thoughtproof Reasoning Check AI skill do?

Why use Thoughtproof Reasoning Check on TypingMind?

Because you install it once and use it with any model. Thoughtproof Reasoning Check is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Thoughtproof Reasoning Check in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/moonpay/skills/tree/main/skills/thoughtproof-reasoning-check. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Thoughtproof Reasoning Check?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Thoughtproof Reasoning Check?

As many as you like. As long as a model supports skills, you can use Thoughtproof Reasoning Check with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Thoughtproof Reasoning Check AI skill free?

Yes. It is published on GitHub by moonpay under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Docs Governance

affaan-m

CommunityPopular

Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks…

Ecc Conventions

Development conventions and patterns for ECC. JavaScript project with conventional commits.

Mcp Dependency Review

affaan-m

CommunityPopular

Statically review MCP configuration for mutable package references before approval or CI, without executing discovered MCP servers. Use when reviewing .mcp.json, Cursor, VS Code, Claude, Windsurf, or…

Skill Host Compat

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

ThoughtProof Reasoning Check

Goal

Prerequisites

Usage

Response

Decision logic

Pricing

Example workflow

MoonPay + ThoughtProof: payment layer + verification layer

Related skills

Frequently asked questions

Related AI Skills

Set up your own AI workspace now