nanoclaw-repl

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

Updated Mar 25, 2026
One-click install
npx skills add https://github.com/Femad-6/my-skills --skill nanoclaw-repl-femad-6
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nanoclaw-repl
Source: https://github.com/Femad-6/my-skills/tree/main/.github/skills/nanoclaw-repl
Command: npx skills add https://github.com/Femad-6/my-skills --skill nanoclaw-repl-femad-6

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Managing persistent, task-focused AI sessions without external dependencies is difficult when you need session history, branching, and search across conversations. This Skill provides operational guidance for running and extending NanoClaw v2, a markdown-backed REPL built on claude -p. ## Core Features & Use Cases - Persistent Sessions: Maintain markdown-backed sessions with history compaction via /compact and metrics via /metrics. - Session Management: Switch models with /model, load skills dynamically with /load, and branch sessions with /branch before high-risk changes. - Search & Export: Search across sessions with /search and export to md, json, or txt with /export for sharing or archival. - Use Case: Before making a risky refactor in a long-running session, branch the session, complete the work, compact the history, and export the result as markdown for your team. ## Quick Start Ask the assistant to start a NanoClaw session, branch before a risky change, and export the session to markdown when finished.

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 AI sessions with NanoClaw REPL?

NanoClaw stores sessions as markdown files, giving you persistent history without a database. Use /compact to condense history after milestones and /metrics to review session statistics.

How to branch and search sessions in a claude -p REPL?

Use /branch to fork the current session before high-risk changes, and /search to run cross-session search across your markdown-backed history. This lets you recover prior context without scrolling through logs.

Does NanoClaw require external dependencies to run?

No, NanoClaw v2 is built with zero external runtime dependencies on top of claude -p. Its extension rules explicitly require keeping handlers deterministic, local, and dependency-free.

Can I export NanoClaw sessions to other formats?

Yes, the /export command converts sessions to markdown, JSON, or plain text. Export before sharing or archiving sessions to preserve a portable record.

What are the limitations of extending NanoClaw?

Extensions must preserve markdown-as-database compatibility and keep command handlers deterministic and local. You cannot introduce external runtime dependencies without breaking the tool's core design constraints.