rg_history

Search Claude session history JSONL files with ripgrep.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/caioniehues/dotfiles --skill rg-history
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rg_history
Source: https://github.com/caioniehues/dotfiles/tree/main/skills/rg_history
Command: npx skills add https://github.com/caioniehues/dotfiles --skill rg-history

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Claude's memory grows with long sessions, but finding past messages, edits, or tool calls can be tedious. This skill provides a simple, ripgrep-powered way to locate relevant history without setting up a vector database or complex indexes.

Core Features & Use Cases

  • Terminal search: Query session history via ripgrep to quickly locate conversations, edits, or decisions.
  • Context-aware snippets: Retrieve small context snippets around matches to stay within output limits.
  • Session file discovery: Locate and inspect session JSONL files in your Claude project structure for quick audits.

Quick Start

Use rg_history to search your memory: for example, search for a term in session.jsonl with:

  • rg 'your_term' session.jsonl Then use scripts/list-sessions.sh to inspect available sessions:
  • scripts/list-sessions.sh /path/to/project

Frequently Asked Questions about rg_history

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

FAQPage Schema
How do I search through my Claude session history without a database?

Search Claude memory fast uses ripgrep to query session JSONL files stored in ~/.claude/projects, retrieving past messages and tool calls directly from your file system without requiring vector databases or complex indexing infrastructure.

Can I find specific messages or edits in my Claude session files?

Yes. rg_history locates past messages, edits, tool calls, and decisions across session history JSONL files by running ripgrep queries with constrained output options to keep results within token limits.

What do I need installed to search my Claude memory?

You need ripgrep installed on your system. rg_history does not rely on vector databases or additional indexing tools—ripgrep and access to your ~/.claude/projects directory are the only prerequisites.

How do I discover and inspect available session files?

Use the included scripts/list-sessions.sh helper script to locate and inspect session JSONL files within your Claude project structure, enabling quick audits of available conversation history.

What's the fastest way to locate context snippets from past interactions?

Search Claude memory fast retrieves small context snippets around matches using ripgrep's constrained output flags (-c, -o, -M), staying within token limits while providing surrounding context for relevance.