Agent skill

claude-code-skill

Manage persistent coding sessions across Claude Code, Codex, Gemini, and Cursor engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, or switching models/tools at runtime. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "switch model", "multi-agent", "coding session", "session inbox", "cursor agent".

View SKILL.md on GitHub Repository
Stars 314
Forks 50

Install this agent skill to your Project

npx add-skill https://github.com/Enderfga/openclaw-claude-code/tree/main/skills

Metadata

Additional technical details for this skill

openclaw 
{
    "emoji": "\ud83e\udd16",
    "install": [
        {
            "id": "npm-plugin",
            "kind": "node",
            "label": "Install plugin (npm)",
            "package": "@enderfga/openclaw-claude-code"
        },
        {
            "id": "node-claude",
            "bins": [
                "claude"
            ],
            "kind": "node",
            "label": "Install Claude Code CLI",
            "package": "@anthropic-ai/claude-code"
        },
        {
            "id": "node-codex",
            "bins": [
                "codex"
            ],
            "kind": "node",
            "label": "Install Codex CLI",
            "package": "@openai/codex"
        },
        {
            "id": "node-gemini",
            "bins": [
                "gemini"
            ],
            "kind": "node",
            "label": "Install Gemini CLI",
            "package": "@google/gemini-cli"
        }
    ],
    "requires": {
        "anyBins": [
            "claude",
            "codex",
            "gemini",
            "agent"
        ]
    }
}

SKILL.md

Claude Code Skill

Persistent multi-engine coding session manager. Wraps Claude Code, Codex, Gemini, and Cursor CLIs into headless agentic engines with 27 tools.

Engine Quick Reference

Engine CLI Session Type Best For
claude claude Persistent subprocess Multi-turn, complex tasks
codex codex exec Per-message spawn One-shot execution
gemini gemini -p Per-message spawn One-shot execution
cursor agent -p Per-message spawn One-shot execution

Core Workflow

bash
# 1. Start session (any engine)
claude-code-skill session-start myproject -d /path/to/project --engine claude
claude-code-skill session-start codex-task -d /path/to/project --engine codex
claude-code-skill session-start gemini-task -d /path/to/project --engine gemini
claude-code-skill session-start cursor-task -d /path/to/project --engine cursor

# 2. Send messages
claude-code-skill session-send myproject "Fix the auth bug" --stream

# 3. Check status / search history
claude-code-skill session-status myproject
claude-code-skill session-grep myproject "error"

# 4. Stop when done
claude-code-skill session-stop myproject

Session Options

Option Description
--engine claude (default), codex, gemini, cursor
--model Model name or alias (opus, sonnet, haiku, gpt-5.4, gemini-pro, composer-2)
--permission-mode acceptEdits, auto, plan, bypassPermissions, default
--effort low, medium, high, max, auto
--max-budget Cost limit in USD
--allowed-tools Comma-separated tool whitelist
--stream Real-time streaming output

Multi-Agent Council

Parallel agent collaboration with git worktree isolation and consensus voting. Agents can use different engines.

bash
# Via TypeScript SDK
manager.councilStart('Build a REST API', {
  agents: [
    { name: 'Architect', emoji: '🏗️', persona: 'System design', engine: 'claude' },
    { name: 'Engineer', emoji: '⚙️', persona: 'Implementation', engine: 'codex' },
  ],
  maxRounds: 5,
  projectDir: '/path/to/project',
});

Council lifecycle: council_start → poll council_status → council_review → council_accept or council_reject.

For details: see references/council.md

Cross-Session Messaging

Sessions can communicate. Idle sessions receive immediately; busy sessions queue.

bash
claude-code-skill session-send-to sender receiver "Auth module needs rate limiting"
claude-code-skill session-send-to monitor "*" "Build failed!"  # broadcast
claude-code-skill session-inbox receiver
claude-code-skill session-deliver-inbox receiver

Team Tools (All Engines)

  • Claude: native /team and @teammate commands
  • Codex/Gemini/Cursor: virtual teams via cross-session inbox routing
bash
claude-code-skill session-team-list myproject
claude-code-skill session-team-send myproject teammate "Review this"

Ultraplan & Ultrareview

  • Ultraplan: Opus deep planning session (up to 30 min), produces detailed implementation plan
  • Ultrareview: Fleet of 5-20 bug-hunting agents reviewing in parallel (security, logic, perf, types, etc.)

Both are async — start then poll status.

27 Tools Overview

Category Tools
Session Lifecycle session_start, send, stop, list, overview
Session Ops status, grep, compact, update_tools, switch_model
Inbox send_to, inbox, deliver_inbox
Teams agents_list, team_list, team_send
Council start, status, abort, inject, review, accept, reject
Ultra ultraplan_start/status, ultrareview_start/status

For full parameter reference: see references/tools.md

Authentication Prerequisites

Each engine requires its own auth before use:

  • Claude: claude /login or ANTHROPIC_API_KEY
  • Codex: codex login or OPENAI_API_KEY
  • Gemini: gemini login or GEMINI_API_KEY
  • Cursor: agent login or CURSOR_API_KEY

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

davila7/claude-code-templates

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

23,776 2,298
Explore
davila7/claude-code-templates

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

23,776 2,298
Explore
davila7/claude-code-templates

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

23,776 2,298
Explore
davila7/claude-code-templates

Claude Code Guide

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.

23,776 2,298
Explore
davila7/claude-code-templates

qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

23,776 2,298
Explore
davila7/claude-code-templates

behavioral-modes

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

23,776 2,298
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results