Where are the generated rules stored?

Rules are synthesized into Markdown files and stored in the .claude/rules/pms/ directory, where they are automatically loaded into Claude's context for future sessions.

How does PMS protect my privacy?

It includes an automatic redaction system that strips API keys, passwords, and sensitive tokens from episodic records before processing or storage.

When should I run the /pms:reflect command?

It is best used at the end of significant work sessions or project milestones to consolidate your learnings into long-term procedural knowledge.

What is the Procedural Memory System (PMS)?

PMS is a skill that helps Claude 'remember' your coding style and preferences by analyzing previous sessions and turning them into persistent rules.

Procedural Memory System (PMS)

Name: Procedural Memory System (PMS)
Author: jcmrs

byjcmrs

Productivity & Workflow

Automates the extraction and persistence of workflows, patterns, and custom rules from Claude Code session history.

About

The Procedural Memory System (PMS) implements a sophisticated three-tier memory architecture—Episodic, Semantic, and Procedural—designed to transform raw conversation transcripts into actionable, long-term knowledge. By analyzing recurring coding patterns, user preferences, and decision-making workflows across multiple sessions, PMS automatically synthesizes context-aware rules that persist in Claude's environment. This skill is essential for developers who want Claude to learn their specific architectural styles, anti-patterns, and project-specific requirements over time, ensuring a more personalized and efficient AI pairing experience.

Key Features

Automatic session transcript encoding with built-in privacy redaction
0 GitHub stars
Semantic pattern extraction for user preferences and code styles
Configurable sensitivity thresholds and automatic event hooks
Three-tier memory architecture for long-term knowledge retention
Automated synthesis of persistent rules in the .claude/rules/ directory

Use Cases

Automating the transition from raw session history to actionable project guidelines
Consolidating architectural patterns and coding standards across long-running projects
Ensuring consistent adherence to team-specific workflows and decision-making processes

About

Key Features

Automatic session transcript encoding with built-in privacy redaction
0 GitHub stars
Semantic pattern extraction for user preferences and code styles
Configurable sensitivity thresholds and automatic event hooks
Three-tier memory architecture for long-term knowledge retention
Automated synthesis of persistent rules in the .claude/rules/ directory

Use Cases

Automating the transition from raw session history to actionable project guidelines
Consolidating architectural patterns and coding standards across long-running projects
Ensuring consistent adherence to team-specific workflows and decision-making processes