name: claude-code-orchestrator description: Use when Codex should spawn, monitor, steer, or review Claude Code agents through the local claude-agent tmux CLI/service, especially for frontend workbench variants and Opus design passes. triggers: - claude-agent - claude code orchestrator - Claude Code agents - Opus variants - workbench variants - manage Claude Code
Claude Code Orchestrator
Use claude-agent when Claude Code should do implementation, frontend exploration, visual variant generation, or review work in the background while Codex keeps orchestration context small.
Defaults
- Model:
opus- resolves to Opus 4.7 on first-party Anthropic. - Effort:
maxby default. Prefer--xhighfor bulk workbench variant sweeps. - Permission mode:
auto. - Runtime: tmux session per agent.
- State:
~/.claude-agent/jobs.
Standard Loop
claude-agent start "Task prompt" --dir /path/to/repo --map --xhigh
claude-agent await-turn <jobId>
claude-agent capture <jobId> 160 --clean
claude-agent send <jobId> "Follow-up instruction"
claude-agent await-turn <jobId>
claude-agent capture <jobId> 220 --clean
Use claude-agent jobs --json for compact status and claude-agent attach <jobId> when a human needs the live tmux session.
Workbench Variant Prompt Shape
Ask Claude Code to read only the compressed design inputs:
Read apps/workbench/AGENT_DESIGN_RULES.md, src/generated/theme-summary.md, and apps/workbench/src/variants/<context>/<brief>/brief.md.
Create v1-v5 as distinct React/Tailwind variants that obey the variant contract.
Run the workbench design check and fix violations.
Report the files changed and the visual direction of each variant.
For bulk variants use --xhigh. For final convergence or hard review use default max.
Local Service
Use the service when another CLI needs to manage agents:
TOKEN="$(claude-agent service token)"
curl -sS -H "Authorization: Bearer $TOKEN" \
-H "content-type: application/json" \
-d '{"prompt":"Review this workbench brief","cwd":"/path/to/repo","effort":"xhigh"}' \
http://127.0.0.1:4877/jobs
Start it with:
claude-agent service start
Rules
- Keep prompts bounded. Link to maps, briefs, and generated summaries instead of pasting large files.
- Use
await-turn, thencapture --clean; do not stream huge tmux logs into the main context. - Use
sendto continue the same agent after scoping so it keeps its local context. - Use
killonly when an agent is stuck or clearly off-track.