By powdream
Invoke external AI agents (Claude, Cursor Agent, Gemini) from Claude Code
Print the full chronological history (prompts and responses) for a specific agent session thread.
Install invoke-agent CLI for the current OS and architecture; download the matching release, place it in a user bin directory, and add that directory to PATH. Supports Windows (cmd, PowerShell), bash, zsh, fish.
List all responder agent sessions mapped to a requester session. Useful to see which agents have been invoked and read their AI-generated summaries.
Retrieve and show agent output by output-id. Use when the user wants to view the result of a previous invoke-agent prompt call using the output ID that was returned.
Invoke an AI agent (claude, cursor-agent, gemini) via invoke-agent CLI. Use when you need to run a cross-agent call bound to an existing session or start a new one.
Invoke external AI agents (Claude, Cursor Agent, Gemini) from the command line and from Claude Code via the invoke-agent plugin.
bun run dev # run without building
bun run build # compile for current and other platforms
bun run src/cmd/main.ts -- --help
This repo is also a Claude Code plugin. It adds skills to invoke the invoke-agent CLI from Claude Code.
/plugin marketplace add powdream/claude-plugins
/plugin install invoke-agent@powdream-plugins
Run Claude Code with the plugin directory:
claude --plugin-dir /path/to/invoke-agent
Then try:
/invoke-agent:install — install the invoke-agent CLI for the current OS/arch and add it to PATH (Windows cmd/PowerShell, bash, zsh, fish)./invoke-agent:claude <prompt> — run a one-off Claude call bound to a Cursor or Gemini session (--cursor-session-id or --gemini-session-id)./invoke-agent:gemini <prompt> — run a one-off Gemini call bound to a Claude or Cursor Agent session (--claude-session-id or --cursor-session-id)./invoke-agent:cursor-agent <prompt> — run a one-off Cursor Agent call bound to a Claude or Gemini session (--claude-session-id or --gemini-session-id)./invoke-agent:output <output-id> — retrieve and show stored agent output (stdout, stderr, etc.) for a given output ID returned by claude/gemini/cursor-agent.--db <path> when running the CLI.See LICENSE if present.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub powdream/claude-plugins --plugin invoke-agentAndroid CLI tools for emulator, adb, and device management
Sub-agent runner — runs agent definitions on Codex, Claude Code, Cursor CLI, or Gemini CLI from any host AI tool.
Complete collection of 117 specialized AI agents across 11 categories
Spawn any third-party LLM provider with an Anthropic-compatible API (e.g. DeepSeek, GLM, Kimi, Qwen, MiniMax) as real Claude Code agent-team teammates or one-shot subagents — driven exactly like native teammates. Your main session's own auth is untouched (OAuth subscription or API key, either works); provider workers bill the provider API key via apiKeyHelper (the key never enters env/argv/history). Requires the `cc-fleet` binary on PATH, installed separately.
Observability platform for Claude Code and Agent SDK — monitor, debug, and control AI coding agents
Cross-agent messaging via SQLite. Send messages between CLI AI agents. No daemon, no network.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.