nanoclaw-repl
affaan-m/everything-claude-code
Zero-dependency session-aware REPL for Claude Code with persistent markdown storage and dynamic skill loading.
What is nanoclaw-repl?
NanoClaw v2 is a REPL environment built on claude -p that maintains persistent sessions in markdown format. Use it when you need interactive multi-turn conversations with model switching, session branching, and searchable history—all without external dependencies.
- Persist conversations to markdown-backed sessions
- Switch models mid-session with /model command
- Dynamically load skills with /load command
- Branch sessions before risky changes with /branch
- Search across sessions with /search
- Compact session history after milestones with /compact
How to install nanoclaw-repl
npx skills add https://github.com/affaan-m/everything-claude-code --skill nanoclaw-replHow to use nanoclaw-repl
- 1.Run scripts/claw.js to start the REPL
- 2.Use /model <name> to switch between available models
- 3.Use /load <skill> to dynamically load additional skills
- 4.Use /branch to create a new session branch before making risky changes
- 5.Use /search <query> to find content across all sessions
- 6.Use /compact to compress session history after completing major work
- 7.Use /export <format> to save sessions as markdown, JSON, or text
- 8.Use /metrics to view session statistics and usage data
Use cases
- Iterative development workflows where you need to save and resume conversations
- Experimenting with different model configurations on the same task
- Exploring multiple solution branches without losing prior work
- Archiving and sharing conversation histories with team members
- Analyzing conversation patterns and metrics across sessions
- Claude Code users building complex multi-turn workflows
- Developers extending or customizing the REPL environment
- Teams needing persistent, searchable conversation records
- Anyone working in zero-dependency environments
nanoclaw-repl FAQ
No. NanoClaw v2 is built with zero external runtime dependencies, keeping it lightweight and portable.
Yes. Use the /model command to switch between available models without losing session context.
Sessions are automatically persisted to markdown files. Use /export to save in other formats like JSON or plain text.
Use /branch to create a separate session branch before making changes, allowing you to preserve the original session.
Yes. The /search command lets you find content across all your sessions.
Full instructions (SKILL.md)
Source of truth, from affaan-m/everything-claude-code.
name: nanoclaw-repl description: Operate and extend NanoClaw v2, ECC's zero-dependency session-aware REPL built on claude -p. metadata: origin: ECC
NanoClaw REPL
Use this skill when running or extending scripts/claw.js.
Capabilities
- 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
Operating Guidance
- Keep sessions task-focused.
- Branch before high-risk changes.
- Compact after major milestones.
- Export before sharing or archival.
Extension Rules
- keep zero external runtime dependencies
- preserve markdown-as-database compatibility
- keep command handlers deterministic and local
Related skills
More from affaan-m/everything-claude-code and the wider catalog.
security-review
Security checklist and patterns for authentication, input validation, secrets, and sensitive features.
golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable applications.
coding-standards
Baseline coding conventions for naming, readability, immutability, and quality across projects.
frontend-patterns
React and Next.js patterns for components, state management, performance, and modern frontend practices.
backend-patterns
REST/GraphQL API design, database optimization, and server-side patterns for Node.js, Express, and Next.js.
golang-testing
Go testing patterns: table-driven tests, subtests, benchmarks, fuzzing, and TDD methodology.