nanoclaw-repl

Operates and extends the session-aware REPL for maintaining claw.js workflows with zero dependencies.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you operate and extend NanoClaw v2’s zero-dependency, session-aware REPL so you can keep context across tasks without losing state or organization.

Core Features & Use Cases

  • Persistent session workflows: Maintains markdown-backed sessions for continuity across runs.
  • REPL command-based control: Supports model switching, dynamic skill loading, session branching, cross-session search, history compaction, and exporting.
  • Operational visibility: Provides session metrics to track progress and usage.
  • Use Case: You’re iterating on a claw script that changes behavior over time; you branch sessions before risky edits, search across prior attempts, compact milestones, and export results for sharing or archival.

Quick Start

Tell the AI to run scripts/claw.js using the nanoclaw-repl skill and then switch to the desired model, branch the session, and export the updated session state.

Frequently Asked Questions about nanoclaw-repl

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

FAQPage Schema
How do I maintain a persistent REPL session across multiple command executions?

Maintain persistent REPL sessions by using a markdown-as-database approach that stores command execution state locally. This ensures context and workflow continuity across multiple runs without external dependencies.

What is the best way to branch a session before making risky edits to a script?

Branch sessions before risky script edits by using a session-aware REPL with built-in branching commands. This preserves your original markdown session state while allowing iterative testing of workflow changes.

Does this REPL environment require any external runtime dependencies?

No, this session-aware REPL requires zero external runtime dependencies. It operates entirely locally, preserving markdown-as-database compatibility while keeping command handlers deterministic.

Can I switch models dynamically during a command execution session?

Yes, you can dynamically switch models and load new skills during an active command execution session. The REPL supports dynamic skill loading to adapt workflow behavior as iterative development tasks evolve.

How do I search across prior session attempts in a markdown database?

Search across prior session attempts by utilizing the cross-session search feature within the markdown database. This queries historical markdown session data to retrieve previous workflow states and milestones.

When should I compact history in a persistent markdown session?

Compact history in a persistent markdown session upon reaching significant milestones to reduce session clutter. History compaction manages markdown database size while preserving essential workflow context for future command executions.