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
This repository also configures its own agents. See what x-agent tells them →
Skill Claude CodeCodex
Delegate tasks or get a second opinion from Claude Code CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Claude Code, or offloading work to it. Do not use for tasks that do not benefit from…
Skill Claude CodeCodex
Delegate tasks or get a second opinion from OpenAI Codex CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Codex CLI, or offloading work to it. Do not use for tasks that do not benefit from…
Skill Claude CodeCodex
Delegate tasks or get a second opinion from Cursor Agent CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Cursor Agent, or offloading work to it. Do not use for tasks that do not benefit from…
Skill Claude CodeCodex
Delegate tasks or get a second opinion from Gemini CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Gemini CLI, or offloading work to it. Do not use for tasks that do not benefit from…
Skill Claude CodeCodex
Delegate tasks or get a second opinion from Junie CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Junie CLI, or offloading work to it. Do not use for tasks that do not benefit from cross-model…
Skill Claude CodeCodex
Delegate tasks or get a second opinion from OpenCode CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with OpenCode, or offloading work to it. Do not use for tasks that do not benefit from…
Skill Claude CodeCodex
Delegate tasks or get a second opinion from Pi CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Pi, or offloading work to it. Do not use for tasks that do not benefit from cross-model input.
Skill Claude CodeCodex
Delegate tasks or get a second opinion from Qwen Code CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Qwen Code, or offloading work to it. Do not use for tasks that do not benefit from…
Skill Claude CodeCodex
Delegate tasks or get a second opinion from Antigravity CLI (agy). Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Antigravity (agy), or offloading work to it. Do not use for tasks that do not…
Skill Claude CodeCodex
Delegate tasks or get a second opinion from jcode CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with jcode, or offloading work to it. Do not use for tasks that do not benefit from cross-model…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: