Cross-harness

2 skills

Delegate work to agents running in other CLI harnesses and coordinate between them.

View this plugin on GitHub

any skills-format agent

$ npx skills add rj11io/11ai --skill 11ai-xharness-agent-comms --skill 11ai-xharness-agent-delegation

claude code

$ claude plugin install 11ai-xharness@11ai

codex

$ codex plugin add 11ai-xharness@11ai

First time? Add the marketplace once with claude plugin marketplace add rj11io/11ai or codex plugin marketplace add rj11io/11ai, then install any plugin from it.

11ai-xharness-agent-comms

Call, spawn, or delegate to an AI agent running in a different harness (Claude Code, Codex CLI, Gemini CLI) and collect its output. Use whenever one agent should hand a task to a model it cannot run itself — for example Codex (GPT 5.6) calling Claude Code (Claude Fable 5) for UI work, or Claude Code calling Codex (GPT 5.6 Luna) to generate a title — including cross-model second opinions, fan-out to parallel workers, and multi-turn sessions with another CLI agent.

11ai-xharness-agent-delegation

Decide which model gets which task when delegating work across harnesses — routes UI, design, and copywriting to Claude Fable 5 (with Sonnet 5 and Opus 4.8 fallbacks) and everything else to a GPT 5.6 tier (Luna, Terra, or Sol) by scope and impact. Use whenever an agent must choose a model for a delegated task, pick between GPT and Claude for a job, apply the team's model routing policy, or resolve a fallback when the assigned model is unavailable.