By seldonframe
Your AI argues before it answers. Five-step decision loop for builders — GATE, LOOK, RESHAPE, ATTACK, CARD — built from Bezos's letters, Musk's algorithm, and Farnam Street's mental models. No more "you're absolutely right!"
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Build, deploy, and sell AI agents from your IDE. One install connects the SeldonFrame MCP: describe a business and get a real hosted workspace — website, booking page, intake form, CRM, and an AI agent — on its own subdomain. First workspace is free, no API key needed.
Build, deploy, and sell AI agents for local-service businesses — from your IDE. One command creates a live hosted workspace on *.app.seldonframe.com: website, booking page, intake form, CRM, and an AI receptionist, in about 3 minutes. No signup, no key for your first workspace. Set SELDONFRAME_API_KEY later to unlock more workspaces, custom domains, and marketplace selling.
Record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift — CI + snapshot tests for MCP tool-call workflows.
npx claudepluginhub seldonframe/reflect --plugin reflectThinking partner for design decisions and architecture brainstorming. Transforms Claude from a solution-provider into a senior engineer thinking partner.
Debate implementation approaches with structured pros and cons analysis
Structured decision-making for AI coding agents. Creates auditable Agent Decision Records (AgDR) when technical choices are made — selecting libraries, patterns, or architecture.
Developer workflow tools: community scanning, technical decision-making
Decomposed reasoning with explicit confidence scoring. Break complex questions into verifiable units, score each independently, and synthesize with uncertainty tracking.
Flexible multi-provider LLM consultations using Python/LiteLLM - includes consultant agent, review/bug-investigation commands, and consultant skill for deep AI-powered code analysis across 100+ models