Opencode

Skill darshitpp/x-agent/opencode

Cross-agent task runner — let any AI CLI (Codex, Cursor, Claude, Gemini, Junie) delegate tasks to or get second opinions from the others

Install

npx -y skills add darshitpp/x-agent --skill opencode

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

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 when already running inside OpenCode CLI or for tasks that do not benefit from cross-model input.

SKILL.md

1.1 KB, as published. Nobody here has run it

Cross-Agent Task Runner — OpenCode CLI

Procedures

Step 1: Self-Call Detection

Check for OPENCODE environment variable, or opencode in process ancestry.
If detected, stop and inform the user: "Cannot invoke OpenCode from within OpenCode. Use a different target CLI."

Step 2: Execute Shared Procedure

Read references/shared-procedure.md for the core workflow (mode inference, context gathering, prompt construction, result presentation).
Read references/cli-opencode.md for OpenCode-specific flags, model selection heuristics, and version compatibility matrix.
Follow the shared procedure using the OpenCode-specific details.