nanoclaw-repl

Operate and extend the NanoClaw v2 REPL with markdown-backed sessions.

Updated Mar 12, 2026
One-click install
npx skills add https://github.com/ryasrk/AgentBrokeTheMatrix-CopilotVersion --skill nanoclaw-repl-ryasrk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nanoclaw-repl
Source: https://github.com/ryasrk/AgentBrokeTheMatrix-CopilotVersion/tree/main/.github/skills/nanoclaw-repl
Command: npx skills add https://github.com/ryasrk/AgentBrokeTheMatrix-CopilotVersion --skill nanoclaw-repl-ryasrk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill provides a powerful and flexible command-line interface for interacting with and extending the NanoClaw REPL, a session-aware tool built on Claude.

Core Features & Use Cases

  • Session Management: Supports persistent markdown-backed sessions, branching, and compaction.
  • Model and Skill Interaction: Allows dynamic model switching and loading of new skills directly within the REPL.
  • Data Handling: Enables exporting sessions to various formats (md, json, txt) and provides session metrics.

Quick Start

Use the nanoclaw-repl skill to export the current session to markdown format.

Frequently Asked Questions about nanoclaw-repl

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

FAQPage Schema
How do I manage persistent Claude CLI sessions with markdown?

You can manage persistent Claude CLI sessions by using a session-aware REPL that backs all data to markdown files. This enables session branching, history compaction, and cross-session search without external databases.

Can I switch Claude models dynamically within an active REPL session?

Yes, you can switch Claude models dynamically within an active REPL session. The tool supports on-the-fly model switching and dynamic skill loading without restarting the session.

How do I export Claude CLI session history to JSON or text?

Exporting Claude CLI session history to JSON or text is done directly through the REPL interface. You can output persistent markdown session data to md, json, or txt formats.

Does this session-aware REPL require any external dependencies?

No, this session-aware REPL operates with zero external runtime dependencies. It adheres to strict extension rules by using markdown-as-database compatibility exclusively, requiring no package installations.

What is the best way to branch an active Claude session without losing history?

The best way to branch an active Claude session is using a REPL with built-in session branching and history compaction. This preserves your original markdown-backed session while creating a divergent context path.