read-memories

Search Claude Code JSONL logs for decisions, patterns, and open TODOs.

Updated Mar 25, 2026
One-click install
npx skills add https://github.com/stackql/stackql-skills --skill read-memories-stackql
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: read-memories
Source: https://github.com/stackql/stackql-skills/tree/main/skills/read-memories
Command: npx skills add https://github.com/stackql/stackql-skills --skill read-memories-stackql

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Search and surface decisions, patterns, and open TODOs from past Claude Code logs to contextualize current work.

Core Features & Use Cases

  • Surface decisions and rationales from past sessions to inform current tasks.
  • Identify patterns and conventions to accelerate new work.
  • Scope-aware recall across all projects or within the current repository.

Quick Start

Ask Claude to search your Claude Code logs for a keyword to retrieve past decisions, patterns, and open TODOs.

Frequently Asked Questions about read-memories

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

FAQPage Schema
How do I recall past decisions and rationale from previous Claude Code sessions?

To recall past decisions from Claude Code sessions, search local JSONL session logs by keyword to surface decisions, patterns, and open TODOs for contextual memory augmentation.

Can I search session logs for context within a specific repository only?

Yes, scope-aware recall lets you search session logs within the current repository only, or apply the search across all projects to retrieve relevant decisions and patterns.

How do I find unresolved TODOs from my previous Claude Code work?

Find unresolved TODOs by searching your local Claude Code JSONL logs to extract and surface open items for ongoing work and contextual recall.

What do I need to extract patterns and decisions from Claude Code session logs?

You need access to local Claude Code JSONL logs, which the Skill parses to extract decisions, patterns, and TODOs for memory augmentation and contextual recall.

What is the best way to surface development patterns and conventions from past AI coding sessions?

Surfacing development patterns from past sessions requires searching local JSONL logs to identify and extract conventions that accelerate new work.