morelogic

    3

    A cognitive reasoning protocol and Markdown-based local memory system for high-stakes AI development and strategy.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    morelogic

    Example session with this skill installed

    Switch to full reasoning mode and analyze the current project architecture for security flaws, then save your findings to the vault.

    • Read your context and instructions
    • Compiled the morelogic

    [LogicMode: full]
    [LogicVault: write security-audit-01]
    Analyzed 7-step reasoning path: Skepticism flagged unencrypted local storage; Self-Reflexivity noted limited container scope.

    Recommendation: Rotate API keys. Detailed audit saved to .agent/memory/ml-vault/logicvault.md.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    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.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    • Increased latency in 'Full' mode due to 7-step reasoning.
    • Memory is local-only: no multi-device sync without Git.
    • Performance depends on the underlying model's base logic.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 months ago

    Permissions

    Browser
    Read Files
    Write Files
    Network Access
    Environment Variables
    Listed5 months ago
    Updated1 month ago

    What's inside

    Frequently Asked Questions

    MoreLogic solves "shallow thinking" and context loss by enforcing a 7-step cognitive protocol for high-stakes decisions and maintaining a local Markdown-based memory named LogicVault. It prevents agents from making repetitive mistakes and ensures architectural constraints are remembered across different terminal sessions.

    This skill is purpose-built for CLI-based environments like Claude Code, Cursor, and other terminal assistants that have local file access. It works by utilizing a specific directory structure (.agent/memory/) within your local project workspace to store context and logs.

    Setup is straightforward and requires no external databases or API keys; once integrated, the skill automatically initializes the LogicVault directory within your project. You can immediately begin using the 7-step reasoning system by toggling between Full, Moderate, or Off modes based on your task's complexity.

    Your purchase includes the full reasoning protocol framework, the LogicVault memory management system, and the audit logging schema. You will also receive periodic updates that refine the cognitive steps and optimize the local memory indexing for faster retrieval.

    Unlike cloud-based RAG systems, MoreLogic stores all project context in plain Markdown files directly in your repository. This makes your agent's "memory" fully transparent, searchable, and version-controllable using standard tools like Git.

    New in Agents & Orchestration