Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
Starts NanoClaw v2 REPL: persistent zero-dependency AI agent session with model routing, skill hot-loading, branching, compaction, export, and metrics.
npx claudepluginhub siniyayousuf/everything_claudecodeHow this command is triggered — by the user, by Claude, or both
Slash command
/everything-claude-code:clawThe summary Claude sees in its command listing — used to decide when to auto-load this command
# Claw Command Start an interactive AI agent session with persistent markdown history and operational controls. ## Usage Or via npm: ## Environment Variables | Variable | Default | Description | |----------|---------|-------------| | `CLAW_SESSION` | `default` | Session name (alphanumeric + hyphens) | | `CLAW_SKILLS` | *(empty)* | Comma-separated skills loaded at startup | | `CLAW_MODEL` | `sonnet` | Default model for the session | ## REPL Commands ## Notes - NanoClaw remains zero-dependency. - Sessions are stored at `~/.claude/claw/<session>.md`. - Compaction keeps the most r...
/clawStarts NanoClaw v2 REPL: persistent zero-dependency AI agent session with model routing, skill hot-loading, branching, compaction, export, and metrics.
/chatSends a message to an OpenClaw assistant and returns its response. Supports optional session parameter for ongoing conversations.
/integrateAnalyzes, enhances, or creates AI artifacts like CLAUDE.md, skills, commands, and hooks to integrate with Subcog persistent memory. Interactive workflow recommended.
/session-continueLoads and continues working in an existing session using the session-management skill's 'Action: continue' section step by step.
/evolveClusters proven patterns from past commands into a proposed reusable Command, Skill, or Agent via the Instinct Engine.
/learnDisplays Claude Code best practices guide on sessions, context, memory, modes, CLI shortcuts, worktrees, and prompting. Also supports specific topics and saving session lessons to persistent memory.
Share bugs, ideas, or general feedback.
Start an interactive AI agent session with persistent markdown history and operational controls.
node scripts/claw.js
Or via npm:
npm run claw
| Variable | Default | Description |
|---|---|---|
CLAW_SESSION | default | Session name (alphanumeric + hyphens) |
CLAW_SKILLS | (empty) | Comma-separated skills loaded at startup |
CLAW_MODEL | sonnet | Default model for the session |
/help Show help
/clear Clear current session history
/history Print full conversation history
/sessions List saved sessions
/model [name] Show/set model
/load <skill-name> Hot-load a skill into context
/branch <session-name> Branch current session
/search <query> Search query across sessions
/compact Compact old turns, keep recent context
/export <md|json|txt> [path] Export session
/metrics Show session metrics
exit Quit
~/.claude/claw/<session>.md.