Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From repowire
Asks a different AI agent backend (e.g., Gemini, Codex) to draft an independent implementation plan before building. Use for a second perspective on task approach.
npx claudepluginhub prassanna-ravishankar/repowire --plugin repowireHow this skill is triggered — by the user, by Claude, or both
Slash command
/repowire:cross-agent-planThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Ask a peer running a **different** agent backend to draft (or critique) a plan,
Refines development plans through multi-round discussions among 3-10 specialized agents selected by domain like frontend, backend, security. Builds consensus on recommendations and trade-offs.
Generator-critic planning: launches 3 parallel explorers with distinct biases (architectural, speed-first, simple-first), then composes best elements into a single plan with attribution. For non-trivial planning tasks.
Requests an independent code/PR/plan review from a different AI agent backend (e.g., Codex reviewing Claude's work) via the repowire mesh. Use for unbiased second opinions before merging.
Share bugs, ideas, or general feedback.
Ask a peer running a different agent backend to draft (or critique) a plan, so the planning perspective is genuinely independent.
repowire config get skills.default_planner_backend
Discover peers/backends: list_peers() (MCP) or repowire peer list (CLI).
delegate) a peer on the
chosen backend.ask(peer_name, "Draft an implementation plan for: <task + constraints>")repowire peer ask is
a synchronous test utility, not this).ask returns a correlation_id; the peer replies via ack(corr_id, <plan>).ask(reply_to=corr_id, ...).Keep the brief tight — state the goal, the constraints, and what a good plan must cover, so the cross-agent plan is comparable to your own.