Claude Code introduces dynamic workflows to orchestrate subagents at scale
steren · x · 2026-08-13
Claude Code has introduced dynamic workflows, a feature that orchestrates subagents at scale using rerunnable JavaScript scripts generated by Claude.
Unlike traditional approaches where a lead agent directly manages other agents, this mode has Claude write an orchestration script executed by a runtime in the background, keeping the current session responsive. By codifying the task plan, this approach increases the robustness of multi-agent collaboration and makes the workflow resumable and rerunnable.
Use cases:
- Tasks requiring more agents than a single conversation can coordinate.
- Codebase-wide bug sweeps or massive migrations involving 500+ files.
- Research tasks requiring cross-checking multiple sources.
- Complex plans worth drafting from several independent angles.
The feature requires Claude Code v2.1.154 or later and is available on all paid plans, Anthropic API, and major cloud platforms.
More from coding & agent
- Devs say LLM coding mistakes are a different class: overcomplication, inferred limits, worse at higher reasoning — Mu5_ · 2026-10-16
- How do you debug bad agent runs when you already have tracing? — Sensitive-Parsnip-12 · 2026-10-16
- Where does pre-task context live for agents? Devs debate workflows beyond handoff — shishen2026 · 2026-10-16
- No-instruction autonomous agent wakes up, sets own goals, and tries hacking by default — sethlazar · 2026-10-16
- CODESTRUCT reframes codebases as AST action spaces to fix brittle LLM code agents — burkov · 2026-10-16
- Would you install another SDK for agent debugging on top of your tracing stack? — Sensitive-Parsnip-12 · 2026-10-16