SURFACE ROUTING — read first This skill hand-rolls subagent orchestration via raw Anthropic API calls. A managed runtime now does the same job. Which one to use depends on your surface: - In Claude Code (incl. CCotw): use the native runtime, NOT this skill. If you can invoke , trigger a run with the keyword, set , or spawn Task subagents — do that instead. The runtime gives 16-concurrent / 1000-agent ceilings, an approval gate, adversarial cross-review, and in-session resume that this skill would otherwise reimplement badly. Dynamic workflows shipped in research preview (Claude Code v2.1.154+…