phantom-ai-coworker — Claude Code skill: agent with memory and VM
phantom-ai-coworker is a Claude Code skill that gives an agent its own machine, vector memory, Slack/email channels, and an MCP server that creates tools at runtime.
no license 781 installs ★ 98 updated 2026-10-09
npx skills add reason-machines/trending-skills --skill phantom-ai-coworker -a claude-codeWhat phantom-ai-coworker does
The agent runs on a separate VM with Docker, stores session context in Qdrant, registers new MCP tools at runtime, and communicates via Slack, Telegram or webhook. Built on Claude Agent SDK with TypeScript/Bun, vector embeddings via Ollama, a self-evolution engine (observe → reflect → propose → validate), and an AES-256-GCM encrypted credential vault.
Requires ANTHROPIC_API_KEY, Qdrant running on localhost:6333, and Ollama for embeddings. Slack channel needs three tokens: SLACK_BOT_TOKEN, SLACK_APP_TOKEN, and SLACK_SIGNING_SECRET. The agent starts an HTTP server on port 3100 and serves an MCP endpoint at http://localhost:3100/mcp, which you can connect to Claude Code via claude_desktop_config.json.
The skill teaches the agent to set up Phantom: clone the repository, edit .env, run docker compose up -d, and check status via /health. Tools that Phantom registers dynamically will become available to all agents connected to its MCP server.
What it helps with
- run an AI agent with persistent memory across sessions
- create MCP tools dynamically without editing config files
- give an agent access to Slack, email, and webhooks for autonomous operation
- deploy infrastructure (databases, dashboards, APIs) on a dedicated VM
- store project context in a vector database with semantic search
Example prompts for the agent
- Set up a Phantom agent on Docker with Qdrant and a Slack channel
- Connect Phantom's MCP server to Claude Code at
http://localhost:3100/mcp - Build a new tool for Phantom that sends a report to Slack every morning
How to install phantom-ai-coworker
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill phantom-ai-coworker -a claude-code2Manually: put the files in place
~/.claude/skills/phantom-ai-coworker/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/phantom-ai-coworker/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill phantom-ai-coworker -a codex2Manually: put the files in place
.agents/skills/phantom-ai-coworker/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill phantom-ai-coworker -a cursor2Manually: put the files in place
.cursor/skills/phantom-ai-coworker/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/trending-skills skills/phantom-ai-coworker2Manually: put the files in place
.github/skills/phantom-ai-coworker/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill phantom-ai-coworker -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/trending-skills --path skills/phantom-ai-coworkerManually: put the files in place
.devin/skills/phantom-ai-coworker/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill phantom-ai-coworker -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about phantom-ai-coworker
How to install phantom-ai-coworker in Claude Code?
Run npx skills add reason-machines/trending-skills --skill phantom-ai-coworker -a claude-code, the skill will appear in ~/.claude/skills/phantom-ai-coworker/SKILL.md.
What does phantom-ai-coworker do?
The skill teaches an agent to deploy Phantom, an autonomous AI coworker with its own VM, vector memory in Qdrant, an MCP server that registers tools at runtime, and communication channels via Slack, email or Telegram.
What dependencies does Phantom need?
Phantom requires Docker (or Bun to run from source), Qdrant running on localhost:6333, Ollama for vector embeddings, and an ANTHROPIC_API_KEY. For Slack channel, you need three tokens: SLACK_BOT_TOKEN, SLACK_APP_TOKEN, and SLACK_SIGNING_SECRET.