pattern-memory

Manage persistent pattern memory to rebuild Council smart-router routing rules.

1|Updated May 12, 2026
One-click install
npx skills add https://github.com/MoxyWolfLLC/moxywolf-plugins --skill pattern-memory-moxywolfllc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pattern-memory
Source: https://github.com/MoxyWolfLLC/moxywolf-plugins/tree/main/plugins/council/skills/pattern-memory
Command: npx skills add https://github.com/MoxyWolfLLC/moxywolf-plugins --skill pattern-memory-moxywolfllc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Pattern-memory solves the problem of improving Council’s routing decisions over time by persistently recording deliberation outcomes, measuring performance (including self-preference bias), and using the resulting data to rebuild routing rules.

Core Features & Use Cases

  • Persistent learning without a backend: Maintains a growing, authoritative workspace JSON file ({workspace}/council-memory.json) that survives Cowork sessions.
  • Value-added scoring for routing: Computes and stores deliberation_value_added to measure whether deliberation beats the best single model for each query category.
  • Dynamic smart-router rule rebuilding: Triggers periodic (and manual) router model rebuilds that derive deliberate vs single_model routing decisions with confidence.
  • Bias and performance tracking: Detects potential self-preference bias, tracks model-level aggregates, and records category-wise strengths/weaknesses.
  • Optional Obsidian vault mirror: Mirrors key memory data to the user’s Obsidian vault as structured, human-browsable notes to create durable cross-linked knowledge.

Quick Start

Ask the Council plugin to deliberate on a question, then call /council-stats after a few deliberations to see category performance and router status.

Frequently Asked Questions about pattern-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I improve multi-model routing decisions over time using JSON persistence?

Multi-model routing decisions improve by logging deliberation outcomes to a persistent JSON file, computing value-added scores, and rebuilding routing rules based on performance data. Pattern-memory automates this cycle.

What is deliberation value-added scoring and how does it measure model performance?

Deliberation value-added scoring measures whether multi-model deliberation beats the best single model for each query category. Pattern-memory computes and stores this metric to evaluate routing effectiveness.

Can I sync deliberation analytics to an Obsidian vault as structured notes?

Yes, you can mirror key memory data to an Obsidian vault as structured, human-browsable notes. This creates durable cross-linked knowledge from your deliberation analytics.

How do I detect self-preference bias in multi-model deliberation workflows?

Self-preference bias is detected by tracking model-level aggregates and category-wise strengths/weaknesses across deliberation outcomes. Pattern-memory records these metrics to identify potential bias.

Do I need a backend database to maintain learning loops for smart routing?

No backend is needed. Pattern-memory maintains a growing workspace JSON file that survives sessions, providing persistent learning without requiring an external database.

When should I trigger a smart-router rule rebuild for multi-model workflows?

Smart-router rule rebuilds should be triggered periodically or manually after sufficient deliberation outcomes are logged. Pattern-memory derives deliberate versus single-model routing decisions with confidence scores.