nanoclaw-repl

Run interactive NanoClaw v2 REPL sessions with persistent markdown-backed state.

Updated Mar 24, 2026
One-click install
npx skills add https://github.com/Oruga420/claude-code-skills --skill nanoclaw-repl-oruga420
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nanoclaw-repl
Source: https://github.com/Oruga420/claude-code-skills/tree/main/nanoclaw-repl
Command: npx skills add https://github.com/Oruga420/claude-code-skills --skill nanoclaw-repl-oruga420

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Operate and extend NanoClaw v2, ECC's zero-dependency session-aware REPL built on claude -p.

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

Quick Start

Start a zero-dependency NanoClaw REPL session in your project to run and extend scripts interactively.

Frequently Asked Questions about nanoclaw-repl

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

FAQPage Schema
How do I start an interactive REPL session with Claude inside my project?

The zero-dependency NanoClaw REPL provides an interactive session within Claude Code workflows, using claude -p to run and extend NanoClaw-based tooling without requiring external runtime dependencies.

Can I switch Claude models dynamically during an active CLI session?

Yes, you can switch models dynamically during an active CLI session by using the /model command, allowing you to adapt the Claude model context without restarting the REPL.

How do I save and export Claude REPL conversation history?

You save and export conversation history using the /export command, which outputs persistent markdown-backed session data to md, json, or txt formats for external use.

Does this interactive Claude session tool require external dependencies?

No, this NanoClaw REPL is strictly zero-dependency, requiring no external runtime packages to manage persistent markdown-backed sessions and execute interactive commands within Claude Code.

How do I branch a conversation or load new skills in a Claude REPL?

You branch an active conversation using /branch and dynamically load new capabilities with /load, extending the interactive session without interrupting the current Claude workflow.

What is the best way to manage long CLI chat histories and prevent context overflow?

Use the /compact command to compress long CLI chat histories, preventing context overflow while maintaining session state. Cross-session search via /search also helps retrieve past interactions efficiently.