/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.
$ npx -y skills add prassanna-ravishankar/repowire --skill delegate --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
/delegate
Context preview
The summary Claude sees to decide when to auto-load this skill.
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.
SKILL.md
delegate.SKILL.mdname: delegate
description: 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.
Delegate a task to a peer
Hand a self-contained task to a peer on a chosen backend and track it via the ask/ack lifecycle.
Resolve the delegate backend
1. **Explicit argument** — if the user named a backend, use it. 2. **Configured default** — else:
repowire config get skills.default_delegate_backend
3. **Safe fallback** — else ask the user which backend to delegate to. Don't hardcode one. (Unlike review/plan, delegation MAY target your own backend — delegating to another claude-code peer is legitimate.)
Choose / create the executor
1. **Prefer an existing peer** on the chosen backend (idle if possible):
- MCP: `list_peers()` → pick an online peer with the right backend.
- CLI: `repowire peer list`.
2. **Spawn only if none exists AND the user is clearly delegating** (don't spawn silently). Confirm before spawning:
- MCP: `spawn_peer(path, backend=<chosen>, circle=<skills.default_circle or current>)`
- CLI: `repowire peer new ...`
Default circle: `repowire config get skills.default_circle` (else your current circle).
Hand off + track
1. Send a complete, self-contained brief (the peer doesn't share your context):
- MCP: `ask(peer_name, "<full task brief + acceptance criteria>")`
- Tracked delegation is MCP-only (`repowire peer ask` is a synchronous test
utility, not the ask/ack lifecycle). To close from the CLI: `repowire peer ack <cid>`. 2. `ask` returns a `correlation_id`; the peer reports back via `ack(corr_id, ...)`. 3. Track to completion; chain follow-ups with `ask(reply_to=corr_id, ...)`.
Use `notify_peer` (fire-and-forget) only for nudges, not for tracked delegation — delegation needs the ack lifecycle.
Read more
name: delegate description: 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.
Delegate a task to a peer
Hand a self-contained task to a peer on a chosen backend and track it via the ask/ack lifecycle.
Resolve the delegate backend
1. **Explicit argument** — if the user named a backend, use it. 2. **Configured default** — else:
repowire config get skills.default_delegate_backend
3. **Safe fallback** — else ask the user which backend to delegate to. Don't hardcode one. (Unlike review/plan, delegation MAY target your own backend — delegating to another claude-code peer is legitimate.)
Choose / create the executor
1. **Prefer an existing peer** on the chosen backend (idle if possible):
- MCP: `list_peers()` → pick an online peer with the right backend.
- CLI: `repowire peer list`.
2. **Spawn only if none exists AND the user is clearly delegating** (don't spawn silently). Confirm before spawning:
- MCP: `spawn_peer(path, backend=<chosen>, circle=<skills.default_circle or current>)`
- CLI: `repowire peer new ...`
Default circle: `repowire config get skills.default_circle` (else your current circle).
Hand off + track
1. Send a complete, self-contained brief (the peer doesn't share your context):
- MCP: `ask(peer_name, "<full task brief + acceptance criteria>")`
- Tracked delegation is MCP-only (`repowire peer ask` is a synchronous test
utility, not the ask/ack lifecycle). To close from the CLI: `repowire peer ack <cid>`. 2. `ask` returns a `correlation_id`; the peer reports back via `ack(corr_id, ...)`. 3. Track to completion; chain follow-ups with `ask(reply_to=corr_id, ...)`.
Use `notify_peer` (fire-and-forget) only for nudges, not for tracked delegation — delegation needs the ack lifecycle.
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 - /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.
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

