/cross-agent-review
Get a code/PR/plan review from a DIFFERENT AI agent over the repowire mesh (e.g. have Codex review Claude's work). Use when you want an independent second opinion from another backend before merging or committing.
$ npx -y skills add prassanna-ravishankar/repowire --skill cross-agent-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/cross-agent-review
Context preview
The summary Claude sees to decide when to auto-load this skill.
Get a code/PR/plan review from a DIFFERENT AI agent over the repowire mesh (e.g. have Codex review Claude's work). Use when you want an independent second opinion from another backend before merging or committing.
SKILL.md
cross-agent-review.SKILL.mdname: cross-agent-review
description: Get a code/PR/plan review from a DIFFERENT AI agent over the repowire mesh (e.g. have Codex review Claude's work). Use when you want an independent second opinion from another backend before merging or committing.
Cross-agent review
Ask a peer running a **different** agent backend to review your work, so the review is genuinely independent (not the same model checking itself).
Resolve the reviewer backend
Pick the reviewer in this order:
1. **Explicit argument** — if the user named a backend (e.g. "review with codex"), use it. 2. **Configured default** — else read it:
repowire config get skills.default_reviewer_backend
(Prints the value, or nothing if unset. `--json` for the raw value.) 3. **Safe fallback** — if still unset, pick any *online peer whose backend differs from yours*, or ask the user which backend to use. **Never** default to your own backend — that defeats the purpose. Never hardcode a specific backend.
You can see who is available and on which backend:
- MCP: `list_peers()`
- CLI: `repowire peer list`
Run the review
1. Find (or spawn) a peer on the chosen backend. 2. Send it a review request with the concrete diff/PR/plan to review. Be specific about what to check.
- MCP: `ask(peer_name, "Review this diff for correctness + bugs: <context>")`
- The tracked ask/ack lifecycle is MCP-only — there's no CLI equivalent for a
non-blocking ask (`repowire peer ask` is a synchronous test utility, not this). 3. `ask` is non-blocking and returns a `correlation_id`. The reviewer closes the thread with `ack(corr_id, <their review>)` — that reply comes back to you. 4. Apply the review; iterate with `ask(reply_to=corr_id, ...)` for follow-ups.
If no different-backend peer is available and the user wants one, spawn it (see the `delegate` skill) — but only with the user's go-ahead.
Read more
name: cross-agent-review description: Get a code/PR/plan review from a DIFFERENT AI agent over the repowire mesh (e.g. have Codex review Claude's work). Use when you want an independent second opinion from another backend before merging or committing.
Cross-agent review
Ask a peer running a **different** agent backend to review your work, so the review is genuinely independent (not the same model checking itself).
Resolve the reviewer backend
Pick the reviewer in this order:
1. **Explicit argument** — if the user named a backend (e.g. "review with codex"), use it. 2. **Configured default** — else read it:
repowire config get skills.default_reviewer_backend
(Prints the value, or nothing if unset. `--json` for the raw value.) 3. **Safe fallback** — if still unset, pick any *online peer whose backend differs from yours*, or ask the user which backend to use. **Never** default to your own backend — that defeats the purpose. Never hardcode a specific backend.
You can see who is available and on which backend:
- MCP: `list_peers()`
- CLI: `repowire peer list`
Run the review
1. Find (or spawn) a peer on the chosen backend. 2. Send it a review request with the concrete diff/PR/plan to review. Be specific about what to check.
- MCP: `ask(peer_name, "Review this diff for correctness + bugs: <context>")`
- The tracked ask/ack lifecycle is MCP-only — there's no CLI equivalent for a
non-blocking ask (`repowire peer ask` is a synchronous test utility, not this). 3. `ask` is non-blocking and returns a `correlation_id`. The reviewer closes the thread with `ack(corr_id, <their review>)` — that reply comes back to you. 4. Apply the review; iterate with `ask(reply_to=corr_id, ...)` for follow-ups.
If no different-backend peer is available and the user wants one, spawn it (see the `delegate` skill) — but only with the user's go-ahead.
May the agents talk . Connect Claude Code, Opencode, Codex, Antigravity, Pi across projects, across machines and with your telegram
Repo: prassanna-ravishankar/repowire
Other skills on repowire.
- /integration-test
Integration test for repowire peer-to-peer messaging. Supports claude-code, opencode, or mixed-agent-type testing with circle boundaries and cross-agent-type communication. Can run all modes in parallel via agent teams.
Open skill - /cross-agent-plan
Get an independent implementation plan from a DIFFERENT AI agent over the repowire mesh before you build (e.g. have Gemini or Codex draft an approach for Claude to critique). Use when you want a second perspective on how to approach a task.
Open skill - /delegate
Hand a task to another AI agent peer over the repowire mesh — reuse an existing peer on the chosen backend, or spawn one if none exists. Use when you want to offload work to a specific agent (e.g. delegate a refactor to a Codex peer) and track it to completion.
Open skill - /repowire-install
Install or update repowire and its skill pack from inside an agent session — ensure the repowire CLI/hooks are set up, install the skills, and verify the mesh works. Use on a fresh machine or to refresh skills to the latest.
Open skill - /repowire-patterns
Reference for how to use the repowire mesh — ask/ack vs notify, broadcast, peer discovery, spawning, and cross-agent workflows. Use when you need to coordinate with other AI agents over repowire and want the right primitive for the job.
Open skill