agents

One CLI for every AI coding agent. Versions, skills, MCP servers, rules — unified across Claude, Codex, Gemini, Cursor, OpenCode, and more.

$ curl -fsSL agents-cli.sh | sh

Or npm install -g @swarmify/agents-cli — also available as ag.

Run any agent. Same interface.

$ agents exec claude "Find all auth vulnerabilities in src/"
$ agents exec codex "Fix the issues Claude found"
$ agents exec gemini "Write tests for the fixed code"

Each agent resolves to the project-pinned version, with the right skills, MCP servers, and permissions already synced. No setup between steps.

Pin versions per project

$ agents add claude@2.0.0      # install specific version
$ agents use claude@2.0.0 -p   # pin to this project

Like .nvmrc for Node. Different projects use different agent versions. A shim reads .agents-version and routes to the right binary automatically.

Install once, every agent gets it

Skills

$ agents skills add gh:yourname/python-expert
$ agents skills list

MCP servers

$ agents search notion
$ agents install mcp:com.notion/mcp

No more running claude mcp add, then codex mcp add, then editing Gemini's config file.

Slash commands

$ agents commands add gh:yourname/commands
$ agents commands list

Markdown format conversion handled automatically — markdown for Claude/Gemini/Cursor, TOML for Codex.

Why

You use multiple coding agents and their configs drift
You want a skill, MCP server, or command installed everywhere
You want to pin agent versions per project like .nvmrc
You want to chain agents in scripts and CI

Supported agents

Claude Code · Codex · Gemini · Cursor · OpenCode · Copilot · Amp · Kiro · Goose · Roo Code

Install

# via curl
$ curl -fsSL agents-cli.sh | sh

# via bun
$ bun install -g @swarmify/agents-cli

# via npm
$ npm install -g @swarmify/agents-cli