Ccc Claw — AI skill for Claude Code
Start NanoClaw v2 — ECC's persistent, zero-dependency REPL with model routing, skill hot-load, branching, compaction, export, and metrics.
How to install Ccc Claw
Installs to ~/.claude/skills/kevinzai-commander-ccc-claw/SKILL.md
mkdir -p ~/.claude/skills/kevinzai-commander-ccc-claw && curl -fsSL https://raw.githubusercontent.com/KevinZai/commander/HEAD/commands/ccc-claw.md -o ~/.claude/skills/kevinzai-commander-ccc-claw/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Ccc Claw does
description: "Start NanoClaw v2 — ECC's persistent, zero-dependency REPL with model routing, skill hot-load, branching, compaction, export, and metrics."
Claw Command
Start an interactive AI agent session with persistent markdown history and operational controls.
Usage
node scripts/claw.js
Or via npm:
npm run claw
Environment Variables
| Variable | Default | Description |
|---|---|---|
CLAW_SESSION |
default |
Session n |
Alternatives in AI
- Ccstatusline — by sirmalloc - A highly customizable status line formatter for Claude Code CLI that displays model info, git b 5.5k ★
- Axonhub — ⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs 3.2k ★
- Claw0 — 0 - 1 learn OpenClaw: sections to build an claw-AI agent from scratch 2.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Octoroute
Smart HTTP router for local LLMs (Ollama, LM Studio, llama.cpp). Rule-based + LLM-powered routing, health chec
Yotta Memory
File-based cross-agent memory standard for AI agents. Zero-dependency CLI (init/remember/recall/forget/archive
Skill MODE Pattern — V1.0
Stolen from: everything-claude-code (ECC) runtime profile system Applied to: AI marketing skills ---
Mastering Langgraph Agent Skill
Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents, branching w
Nanoclaw Skills
Official skill marketplace for NanoClaw — a lightweight AI assistant that runs agents in isolated containers.
Vibeharness
Hackable, interactive LLM agent harness for the terminal — streaming REPL, tool-using agent loop, persistent P
Related Agents
Grow Agent
Session orchestrator for one domain. Owns Rule 20a session-start gate + Rule 4 goal-driven loop + Rule 22 deci
Perf Tester
Use to measure latency, throughput, and load behaviour of HTTP endpoints or hot functions with autocannon or k
System Agent
Maintains system/hot.md and system/agent-log.md only. Use at session start and end.