model-first-reasoning
Model-First Reasoning (MFR)
A rigorous methodology that REQUIRES constructing an explicit problem MODEL before any reasoning or implementation. The model becomes a frozen contract that governs all downstream work.
Based on Kumar & Rana (2025), "Model-First Reasoning LLM Agents: Reducing Hallucinations through Explicit Problem Modeling" (arXiv:2512.14474)
Why MFR Works
Hallucination is not merely the generation of false statements—it is a symptom of reasoning performed without a clearly defined model of the problem space.
Reasoning does not create structure; it operates on structure. When that structure is implicit or unstable, reasoning becomes unreliable. MFR provides "soft symbolic grounding"—enough structure to stabilize reasoning without imposing rigid formalism.
Core Principle
Phase 1 produces the MODEL. Phase 2 reasons/implements ONLY within the model.
This prevents the common failure mode where reasoning introduces ad-hoc decisions, missing constraints, or invented behavior not grounded in the problem definition.
Non-Negotiable Rules
More from petekp/claude-code-setup
code-comments
Write clear, plain-spoken code comments and documentation that lives alongside the code. Use when writing or reviewing code that needs inline documentation—file headers, function docs, architectural decisions, or explanatory comments. Optimized for both human readers and AI coding assistants who benefit from co-located context.
139design-critique
Critique UI/UX designs for clarity, hierarchy, interaction, accessibility, and craft. Use for design reviews, PR feedback on UI changes, evaluating mockups, checking if a component is ship-ready, or when honest feedback is needed on whether something meets a high bar.
46personality-profiler
Generate rich personality profiles from social media data exports (Twitter/X, LinkedIn, Instagram). Use when a user wants to analyze their social media presence, create a personality profile for AI personalization, understand their communication patterns, or extract insights from their digital footprint. Triggers on requests like "analyze my Twitter data", "create a personality profile", "what can you learn about me from my posts", "personalize an AI for me", or when users provide social media export files.
40swiftui
Use when building SwiftUI interfaces for iOS, iPadOS, macOS, or visionOS. Triggers on Liquid Glass adoption, SwiftUI animation/transitions, layout patterns, state management, design tokens, performance optimization, accessibility in SwiftUI, or creating "Apple-level" UI quality.
39deep-research
|
36unix-macos-engineer
Expert Unix and macOS systems engineer for shell scripting, system administration, command-line tools, launchd, Homebrew, networking, and low-level system tasks. Use when the user asks about Unix commands, shell scripts, macOS system configuration, process management, or troubleshooting system issues.
36