X Agent — AI skill for Claude Code
Cross-agent task runner — let any AI coding CLI (Codex, Cursor, Claude Code, Gemini, Junie, Qwen, OpenCode, Pi, Antigravity, jcode) delegate tasks to or get second opinions from the others.
How to install X Agent
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open darshitpp/x-agent and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What X Agent does
Cross-agent task runner — let any AI coding CLI (Codex, Cursor, Claude Code, Gemini, Junie, Qwen, OpenCode, Pi, Antigravity, jcode) delegate tasks to or get second opinions from the others.
Alternatives in AI
- AI Dev Tasks — A simple task management system for managing AI dev agents 7.8k ★
- Agmsg — Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other 1.5k ★
- Claude Delegator — Delegate tasks to Codex GPT 5.2 directly from within Claude Code 909 ★
README
x-agent
Let your AI coding agent talk to other AI coding agents.
x-agent is a set of [agentskills.io](https://agentskills.io) skills that enable any AI CLI tool — Codex, Cursor, Claude Code, Gemini CLI, Junie, Qwen Code, OpenCode, Pi, Antigravity (agy), jcode — to delegate tasks to or get second opinions from the others. Install it once, and your agent gains the ability to call any of the others.
Why
Every model has blind spots. A single model reviewing its own output is like proofreading your own writing — you miss things. x-agent fixes this by letting your agent bring in a different model family for a genuine second opinion.
- Catch what one model misses. Claude might miss a concurrency issue that Gemini catches. Codex might spot an API misuse that Cursor overlooks. Cross-model validation surfaces real problems, not just style preferences.
- Use the right model for the job. Some models are better at reasoning about architecture, others at writing code fast. Instead of being locked into one, delegate the task to whichever model fits best.
- No copy-paste workflow. Without x-agent, cross-validating means manually copying context between terminals. x-agent handles context gathering, prompt construction, model selection, and result synthesis automatically.
When to use it
| Situation | Mode | What happens |
|---|---|---|
| You finished a plan and want a sanity check before building | Validation | Sends the plan to a different model family, returns a structured comparison with agreement, counterpoints, and synthesis |
| You have a PR and want a review from a different perspective |
Related Skills
Ask All
Ask GPT, Gemini, Grok, and any configured OpenRouter models in parallel for independent second opinions, then
Ultracodex
Blend Codex headless into Claude Code's Workflow (ultracode) orchestration — cross-model adversarial verificat
Orchestra Board
🎼 Be the maestro of your AI orchestra. A desktop canvas where you drop Claude Code, Codex and other CLI agent
Polyagent MCP
Let any AI agent (Claude Code, Codex, Gemini/Antigravity) delegate to the Cursor CLI agent via MCP: cheap/fast
Cursor MCP Bridge
Let any AI agent (Claude Code, Codex, Gemini/Antigravity) delegate to the Cursor CLI agent via MCP: cheap/fast
Claude MCP Bridge
Let any AI agent (Cursor, Codex, Gemini/Antigravity) delegate to Claude Code via MCP: adversarial code review,
Related Agents
Paf Reviewer
Runs one phone-a-friend relay or review command in the background and reports back a receipt plus the findings
Consult Agent
Execute cross-tool AI consultations via Task spawning. Use when agents or workflows need a second opinion from
Gemini Delegate
Delegate broad, purely reading analysis over a lot of material to Gemini (Antigravity CLI) — condense large di