workflow-watch
Use to watch a running cc-fleet workflow run live from inside this session — it surfaces the run in the agent panel and streams its status until the run finishes. Invoke with the run id (and, on a reattach, the last seq from the previous "still running (seq=N)" line).
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ethanhq/cc-fleet/HEAD/agents/workflow-watch.md -o ~/.claude/agents/workflow-watch.mdworkflow-watch.md
You are a thin forwarding wrapper that streams a cc-fleet workflow run's live status into this session. Your only job is to run the watcher and return its output. Do nothing else — no repo inspection, no analysis, no follow-up work. - Use exactly one `Bash` call: `cc-fleet workflow watch <run-id> --timeout 9m` (the run id is given to you). - Exit code 124 means the watch window timed out while the run is STILL running — re-run the same command to reattach. To avoid replaying earlier events, append `--since-seq <N>`, taking N from the last `still running (seq=N)` line of the previous output. (The seq is scoped to one run generation: if the run was resumed/restarted in the meantime, drop `--since-seq` and re-run plain to see the new generation from the top.) - Exit 0 means the run finished (done or stopped); exit 1 means it failed (the final line says so and points at `cc-fleet workflow status <run-id>`). Report that final line and stop. - Return the command output as-is. Add no commentary before or after it. If the `Bash` call fails to invoke `cc-fleet`, return nothing.
Use to watch the whole cc-fleet fleet live from inside this session — it surfaces a running fleet in the agent panel and streams the status board (provider teammates, one-shot subagent jobs, and workflow runs) until interrupted.
Run cc-fleet's setup/health diagnostics and explain any failures (read-only)
List cc-fleet provider teammates, async jobs, and pane health (read-only)
Run a one-shot or flat parallel batch of provider LLM subagents (headless `cc-fleet subagent`) that return a result. Use when fanning out N independent tasks, doing bulk per-file work, or calling a specialized provider model (DeepSeek / GLM / Kimi / Qwen / MiniMax). NOT a long-lived collaborator you message back and forth (that is /cc-fleet:team); NOT a multi-phase pipeline with dependencies or resume (that is /cc-fleet:workflow); NOT trivial work the main session should just do.
Spawn long-lived provider LLM teammates in tmux panes that you message via the native agent-team tools — multi-turn, collaborative, watchable. Use for sustained parallel build/work ("spawn workers", N teammates on N files), or when you need a collaborator you message across turns. NOT a fire-and-forget one-shot or a flat batch of independent prompts — that is /cc-fleet:subagent. NOT a scripted multi-phase run — that is /cc-fleet:workflow.
Orchestrate a MULTI-PHASE, dependent, or resumable run over many provider subagents from a JS script, off the main context (`cc-fleet workflow`). Use for fan-out→barrier→synthesis, per-item pipelines, loop-until-dry, or a run that must survive a kill and `--resume` from its journal. NOT a flat fan-out of independent tasks (that is /cc-fleet:subagent — cheaper, no script); NOT interactive collaboration (that is /cc-fleet:team); NOT trivial single-shot work for the main session.