---
name: Cross Agent Plan
slug: cross-agent-plan
category: AI Engineering
description: Cross Agent Plan gets an independent implementation plan or critique from a different AI backend before you build. Use it when you want a second perspective on an approach or want to compare plans across agents.
github: "https://github.com/prassanna-ravishankar/repowire/tree/main/skills/cross-agent-plan"
language: Go
stars: 260
forks: 34
install: "npx degit https://github.com/prassanna-ravishankar/repowire/tree/main/skills/cross-agent-plan ~/.claude/skills/cross-agent-plan"
installs_to: ~/.claude/skills/cross-agent-plan
source_path: skills/cross-agent-plan/SKILL.md
collection_size: 17
category_size: 2631
collection_url: "https://dirskills.com/collections/prassanna-ravishankar/repowire"
added: 2026-09-02T05:20:16.047Z
last_synced: 2026-09-02T05:20:16.047Z
canonical_url: "https://dirskills.com/skills/cross-agent-plan"
---

# Cross Agent Plan

Cross Agent Plan gets an independent implementation plan or critique from a different AI backend before you build. Use it when you want a second perspective on an approach or want to compare plans across agents.

**Install:**

```bash
npx degit https://github.com/prassanna-ravishankar/repowire/tree/main/skills/cross-agent-plan ~/.claude/skills/cross-agent-plan
```

## README

# Cross-agent plan

Ask a peer running a **different** agent backend to draft (or critique) a plan,
so the planning perspective is genuinely independent.

## Resolve the planner backend

1. **Explicit argument** — if the user named a backend, use it.
2. **Configured default** — else:
   ```bash
   repowire config get skills.default_planner_backend
   ```
   (Empty output means unset.)
3. **Safe fallback** — else pick an online peer on a backend *different from yours*,
   or ask the user. Never default to your own backend; never hardcode one.

Discover peers/backends: `list_peers()` (MCP) or `repowire peer list` (CLI).

## Run the planning round

1. Find (or, with the user's go-ahead, spawn — see `delegate`) a peer on the
   chosen backend.
2. Send the task + constraints and ask for a concrete step-by-step plan.
   - MCP: `ask(peer_name, "Draft an implementation plan for: <task + constraints>")`
   - Tracked ask is MCP-only (no CLI lifecycle equivalent — `repowire peer ask` is
     a synchronous test utility, not this).
3. `ask` returns a `correlation_id`; the peer replies via `ack(corr_id, <plan>)`.
4. Critique/merge the returned plan with your own; chain follow-ups with
   `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.