morelogic

What it does

MoreLogic is a high-precision reasoning and local memory framework designed for CLI-based AI agents. It implements a sophisticated 7-step cognitive protocol—covering Judgment, Skepticism, Sensitive Reading, Rationality, Originality, Activist Engagement, and Self-Reflexivity—to transform standard model outputs into vetted, audit-aware architectural and strategic decisions. It includes a robust file-based memory system, LogicVault, which allows agents to maintain long-term project context, decision logs, and trust settings directly within your local workspace.

Why use this skill

Standard prompting often suffers from "shallow thinking" or context loss between sessions. MoreLogic forces the agent to internally simulate critical thinking and verify facts before providing an answer. It replaces ephemeral context with a durable Markdown memory layer, ensuring your agent remembers architectural constraints, project-specific quirks, and past decisions across different sessions without needing an external database or expensive RAG infrastructure.

Supported tools

• CLI Agents: Optimized for Claude Code, Cursor, and other terminal-based AI assistants.
• Local Filesystem: Uses standard Markdown files in .agent/memory/ for transparent, version-controllable memory.
• Reasoning Modes: Configurable Full, Moderate, and Off modes to balance rigor and performance.

Output

In high-stakes modes, the agent provides deeply rationalized answers that explicitly state limitations, cite local memory entries, and flag potential contradictions. It also maintains a structured audit.md log of all memory mutations for full traceability.