subagent
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.
npx skills add ethanhq/cc-fleet --skill subagent --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# subagent — one-shot / batch / background provider subagent **Wrong lane?** A long-lived collaborator you message back and forth → /cc-fleet:team; a multi-phase pipeline with dependencies or resume → /cc-fleet:workflow; arbitration in cc-fleet-shared/routing.md. When this skill cites `cc-fleet-shared/<file>.md`, OPEN it with the Read tool at `../cc-fleet-shared/<file>.md` relative to this SKILL.md — the cited content is load-bearing, not optional background. > **Execution environment — check before running anything.** Confirm your shell tool executes on the host where cc-fleet is installed. In sandboxed or remote agent sessions, a tool named Bash may run on an isolated machine with a different filesystem, PATH, processes, and tmux server — `command not found`, a healthy-looking `doctor` whose leaves can't reach your files, or a wrong working directory should prompt you to verify whether you are in a sandbox shell, not conclude that cc-fleet is broken. If so, route commands through a host-executing bridge tool (for example, desktop-commander) and pass host paths for any files you reference; do not retry the same Bash call expecting different results. If no host-executing tool is av
- When to use it
- The provider ask ladder (ask at most once per task)
- Calling it (run via Bash, always with --json)
- Success envelope
- Failure envelope — dispatch on errorcode (do not parse prose)
- Batch fan-out (parallel, each returns synchronously)
- Long tasks: a backgrounded Bash is the push notification
- Multi-turn: --resume
- Cleanup vs. resume — they're independent
- Anti-patterns
cc-fleet subagent claude --model opus --prompt "<synthesis over the gathered notes>" --json
cc-fleet subagent --prompt "<task>" --json # no provider arg → default provider
cc-fleet subagent deepseek --model strong \
Optional explicit override, with a known team:
cc-fleet subagent --prompt "..." --lead-session-id "$lead_session_id" --json
These Bash calls are independent and can fire in parallel; subagent is
cc-fleet subagent glm --prompt "Summarize docs/a.md" --json
cc-fleet subagent glm --prompt "Summarize docs/b.md" --json
cc-fleet subagent deepseek --prompt "Summarize docs/c.md" --json
Each returns its own {ok, result, total_cost_usd}; aggregate them. NoWhat does the subagent skill do?
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.
How do I install it?
Run `npx skills add ethanhq/cc-fleet --skill subagent --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ethanhq/cc-fleet, a repository with 201 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.