nanoclaw-repl

Run session-aware NanoClaw v2 experiments with markdown-backed storage and model switching.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/GGEdu/claude-god-mode-template --skill nanoclaw-repl-ggedu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nanoclaw-repl
Source: https://github.com/GGEdu/claude-god-mode-template/tree/main/docs/patterns/nanoclaw-repl
Command: npx skills add https://github.com/GGEdu/claude-god-mode-template --skill nanoclaw-repl-ggedu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

NanoClaw REPL provides a lightweight, session-aware environment for running and extending NanoClaw v2 with Claude, delivering zero-dependency operation and easy session management.

Core Features & Use Cases

  • persistent markdown-backed sessions
  • model switching with /model
  • dynamic skill loading with /load
  • session branching with /branch
  • cross-session search with /search
  • history compaction with /compact
  • export to md/json/txt with /export
  • session metrics with /metrics Use cases: developers can experiment with prompts, compare model outputs, branch sessions to preserve experiments, and export results for documentation.

Quick Start

Launch the NanoClaw REPL by running scripts/claw.js to start a session and interact with Claude.

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 REPL sessions with Claude?

You can manage persistent REPL sessions with Claude using markdown-backed session storage, which preserves experiment state without external databases. The environment supports branching, cross-session search, and history compaction to maintain context across interactions.

Can I run a Claude-powered REPL without installing dependencies?

Yes, you can run a zero-dependency Claude-powered REPL by executing the core launch script directly. This standalone operation requires no external library installations, enabling deterministic command handling and dynamic skill loading in isolated environments.

How do I branch and export Claude prompt experiments?

To branch and export Claude prompt experiments, use the dedicated session branching command to fork conversations, then apply the export command to output results in markdown, JSON, or text formats for documentation and comparison.

How do I switch models during a Claude REPL session?

You can switch models dynamically during a Claude REPL session by issuing the specific model-switching command. This allows you to compare outputs from different models within the same persistent workflow without restarting the environment.

What are the limitations of markdown-backed session storage for REPL?

Markdown-backed session storage for REPL limits complex querying and concurrent write operations compared to database-driven systems. It is best suited for lightweight, deterministic experimentation and single-user developer workflows rather than high-scale concurrent environments.