ChengRang

Claude Code Dynamic Workflows

AI Coding Paid

Anthropic feature launched with Opus 4.8 on 2026/5/28: one workflow command spawns dozens to hundreds of sub-agents, HN 198 points

AnthropicClaude CodeAgent CollaborationDynamic WorkflowMulti-Agent
Visit Claude Code Dynamic Workflows

Disclaimer: Review content represents our editorial team's views and experience, not commercial recommendation or investment advice. Product info and pricing may change; refer to official sources.

Overview

Dynamic Workflows is a new Claude Code feature launched by Anthropic on May 28, 2026, alongside Claude Opus 4.8, with a HN score of 198. It upgrades Claude Code from 'a single AI working alone' to 'an AI orchestrating dozens to hundreds of AIs collaborating.'

The usage is simple: you input a sentence in Claude Code with the word 'workflow.' Instead of working alone, Claude first writes a scheduling script, then dispatches dozens or even hundreds of sub-agents to work in parallel and review each other, finally merging and delivering the results. This is an official native Multi-Agent solution for large-scale engineering tasks, similar in positioning to open-source Multi-Agent frameworks like OpenHands / SWE-Agent but with deeper integration.

Key Features

Use Cases

Pros

Pricing

Requires Claude Code v2.1.154 or later. Available on all paid plans (including Pro, Max, and API accounts), and supports Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. Multi-agent parallelism significantly increases token consumption; running hundreds of sub-agents in one round may consume millions to tens of millions of tokens—heavy usage is recommended with API billing and Prompt Caching optimization. Pro users need to enable Dynamic Workflow in /config.

Summary

Dynamic Workflows is primarily aimed at developers and teams with truly large-scale engineering tasks—scenarios like framework migration, cross-repository transformation, and codebase-level refactoring. For daily small projects, a single agent is sufficient. Its real value lies in lowering Multi-Agent collaboration from an 'advanced technique' to a 'one-command native capability,' serving as Claude Code's direct response to competitors like Cursor / Devin in terms of Harness depth.

Category
AI Coding
Pricing
Paid
Tags
Anthropic · Claude Code · Agent Collaboration
Website

Related Tools