cross-agent-plan — Claude Code skill: a plan from another agent
Asks a local coding agent for an implementation plan or a design critique through the Repowire remote MCP server.
npx skills add prassanna-ravishankar/repowire --skill cross-agent-plan -a claude-codeWhat cross-agent-plan does
This skill is for the moments when a second opinion helps. It hands a task to an agent on another machine and brings back that agent's plan. First list_machines and list_agents locate an agent holding context for the project. Unless the user picked a backend, the skill suggests a different one so the answer is not an echo of your own.
Then comes ask_agent, called with exact machine and peer IDs. The request carries the goal, the constraints, design context and the tradeoffs you care about. Planning is the whole scope here — the skill states that no implementation is authorised by this request. Keep the returned request ID and pull the answer with get_reply, which can wait up to 20 seconds. A pending status means the work is still running.
Read the plan, then list the choices it leaves open. Treating it as a green light to start coding is not what the skill does. When sending times out, check list_requests for work already in flight before retrying. One hard limit: the remote tools cannot spin up a planner session that does not exist.
What it helps with
- get an implementation plan from an agent with different context
- test a design against an outside opinion before writing code
- locate a machine and agent suited to the task
- fetch the reply to an async request by its ID
- turn a returned plan into a list of open questions
Example prompts for the agent
- Find an agent with project context via
list_machinesandlist_agents, then ask for a plan to refactor the billing module - Send the goal and constraints through
ask_agent, wait for the reply and show me the unresolved choices - Check
list_requestsif the send hangs instead of retrying blindly
How to install cross-agent-plan
1Skills CLI (Vercel)
npx skills add prassanna-ravishankar/repowire --skill cross-agent-plan -a claude-code2Manually: put the files in place
~/.claude/skills/cross-agent-plan/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/cross-agent-plan/
1Skills CLI (Vercel)
npx skills add prassanna-ravishankar/repowire --skill cross-agent-plan -a codex2Manually: put the files in place
.agents/skills/cross-agent-plan/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add prassanna-ravishankar/repowire --skill cross-agent-plan -a cursor2Manually: put the files in place
.cursor/skills/cross-agent-plan/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install prassanna-ravishankar/repowire cross-agent-plan2Manually: put the files in place
.github/skills/cross-agent-plan/SKILL.md1Skills CLI (Vercel)
npx skills add prassanna-ravishankar/repowire --skill cross-agent-plan -a gemini-cli2Platform CLI
gemini skills install https://github.com/prassanna-ravishankar/repowire --path plugins/repowire-remote/skills/cross-agent-planManually: put the files in place
.devin/skills/cross-agent-plan/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add prassanna-ravishankar/repowire --skill cross-agent-plan -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about cross-agent-plan
How do I install cross-agent-plan in Claude Code?
Run npx skills add prassanna-ravishankar/repowire --skill cross-agent-plan -a claude-code. The skill lands at ~/.claude/skills/cross-agent-plan/SKILL.md.
What does cross-agent-plan do?
It uses the Repowire remote MCP server to ask a local coding agent for an implementation plan or a design critique, then retrieves that answer by request ID.
Can I start implementing straight from the returned plan?
No. The request covers planning only and grants no permission to execute, so the plan needs your review first.
