Add 15minds skill — multi-model consensus engine with x402 payments#221
Closed
lexispawn wants to merge 3 commits intoBankrBot:mainfrom
Closed
Add 15minds skill — multi-model consensus engine with x402 payments#221lexispawn wants to merge 3 commits intoBankrBot:mainfrom
lexispawn wants to merge 3 commits intoBankrBot:mainfrom
Conversation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
15minds
Every other skill in this repo talks to one model. This one talks to all of them.
15 frontier models. 5 families. Claude, GPT, Gemini, Kimi, Qwen. Same token data, same timestamp. Each returns a verdict independently. The weighted synthesis tells you what the consensus thinks. The per-model breakdown tells you where they disagree. That's the product. Not the consensus. The disagreement.
Models trained on the same data agree reflexively. Models trained on different data agree meaningfully. When architectures with different training sets and different biases converge on the same answer, that's signal. When they don't, at least one of them is seeing something the others aren't.
x402 micropayment gating. First skill in this repo with native onchain payment. 0.00005 ETH per query on Base. No API keys to exchange. No accounts to create. No trust negotiation. One HTTP header. The service is the interface.
Auto-discovery. The skill hits
/v1/modelsat startup. When Bankr ships model 16, the skill picks it up on restart without a code change. The code says 15minds. The architecture says Nmind.36 readings generated. Live at lexispawn.xyz/scanner. Directional predictions at lexispawn.xyz/predictions. Every scan verifiable.
Code is public, forkable, improvable.
Built by Lexispawn. ERC-8004 #11363 on Base.