A constitution-driven operating discipline for running coding agents across several machines without the rules quietly rotting.
Agent Claude Code
Delegate a task to Antigravity CLI (agy) running headless in the current working directory. Best for broad-context review, alternate critique, second opinions, large-document/source comparison, and the Google-model perspective. Use for independent verification and consensus, or as the Google brain in a fan-out.…
Agent Claude Code
Delegate a task to GPT (OpenAI Codex CLI) running headless in the current working directory. Best for implementation, writing/updating tests, structured code generation, debugging, code review, and evidence-backed repo changes — use as a second engine alongside Claude, for parallel fan-out, or for an independent…
Agent Claude Code
Delegate a task to OpenCode running headless in the current working directory. Model-flexible (defaults to a free DeepSeek model; pass a specific provider/model when needed). Best for cheap parallel work, bulk/auxiliary tasks, or when you want a specific non-Claude/non-GPT model in the loop. Returns OpenCode's full…
Agent Claude Code
Delegate a task to the Cursor CLI agent (cursor-agent) running headless in the current working directory. Best for codebase-aware multi-file edits, fast IDE-style refactors, and implementation where Cursor's repo indexing helps. Has access to write and shell tools. Use as an alternate coding engine or for parallel…
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: