Coordinate agents
You stay the architect: you write the brief, review every result and integrate it. Delegated
output is untrusted until you have read the diff and run the checks.
When to split
Only for work that is genuinely independent (separate files or modules, a clear acceptance check)
or a second opinion. Keep tightly coupled work in one agent. Small tasks you can finish in a few
steps stay with you.
Who gets which work
Follow ~/agent-skills/shared/agent-routing.md: UI work goes to Codex, simple isolated tasks to
Antigravity (--agent antigravity), complex work stays with you. When a run reports
quotaExhausted, move to the next agent in that row.
Delegated implementation (Codex, Antigravity, OpenCode)
Follow workflows/codex-implement.md with the agent the routing picked: brief file, its own
worktree, codex-bridge run --agent <agent> --sandbox workspace-write, then review and bring the
change back. Bridge rules are in ~/agent-skills/shared/codex-bridge.md.
Parallel subagents (Claude)
One goal per agent, a brief that stands alone (files to read, what is ruled out, the output
format), launched in a single message. For edits, give each its own worktree. Record each agent's
task and status in a ledger when there are more than two.
Integrate
Read each diff, run the tests, resolve conflicts yourself, verify the result (verify) and get a
review of large changes (review-code). Report which agent did what and anything that failed.
1---2name: coordinate-agents3description: Split work across agents — delegate an isolated implementation to OpenAI Codex through codex-bridge in its own git worktree, run independent parts in parallel subagents, then review and integrate the results yourself. Includes the former /codex-frontend workflow. Use for "use Codex for this", "delegate to Codex", "split this work", "run agents in parallel" or "orchestrate agents".4metadata:5 source: https://skillmd.com/skills/amsborse/coordinate-agents6 aliases: "use codex, delegate to codex, codex frontend, split this work, parallel agents, orchestrate agents, multi agent"7 keywords: "codex, antigravity, agy, delegate, agents, subagents, parallel, worktree, orchestrate, handoff, opencode, routing, fallback"8 composes: "review-code, verify"9 requires: "codex-bridge?, subagents?, git"10 risk: "medium"11---1213# Coordinate agents1415You stay the architect: you write the brief, review every result and integrate it. Delegated16output is untrusted until you have read the diff and run the checks.1718## When to split1920Only for work that is genuinely independent (separate files or modules, a clear acceptance check)21or a second opinion. Keep tightly coupled work in one agent. Small tasks you can finish in a few22steps stay with you.2324## Who gets which work2526Follow `~/agent-skills/shared/agent-routing.md`: UI work goes to Codex, simple isolated tasks to27Antigravity (`--agent antigravity`), complex work stays with you. When a run reports28`quotaExhausted`, move to the next agent in that row.2930## Delegated implementation (Codex, Antigravity, OpenCode)3132Follow `workflows/codex-implement.md` with the agent the routing picked: brief file, its own33worktree, `codex-bridge run --agent <agent> --sandbox workspace-write`, then review and bring the34change back. Bridge rules are in `~/agent-skills/shared/codex-bridge.md`.3536## Parallel subagents (Claude)3738One goal per agent, a brief that stands alone (files to read, what is ruled out, the output39format), launched in a single message. For edits, give each its own worktree. Record each agent's40task and status in a ledger when there are more than two.4142## Integrate4344Read each diff, run the tests, resolve conflicts yourself, verify the result (`verify`) and get a45review of large changes (`review-code`). Report which agent did what and anything that failed.