@_vmlops: ANTHROPIC QUIETLY SHIPPED /workflows IN CLAUDE CODE and the principle behind it is what got me old pattern → one LLM or…
Summary
Anthropic quietly shipped /workflows in Claude Code, replacing LLM orchestrators with code-based control flow to avoid token tax and context sloppiness.
View Cached Full Text
Cached at: 05/23/26, 02:12 PM
ANTHROPIC QUIETLY SHIPPED /workflows IN CLAUDE CODE
and the principle behind it is what got me
old pattern → one LLM orchestrates everything. spawns sub-agents, holds every result, plans the next step
the problem…? every sub-agent result re-enters the orchestrator’s context spin up 10 agents and your main session pays a “token tax” getting sloppier as the window fills.
/workflows replaces the LLM orchestrator with code
you define a workflow.js file. code handles the control flow. the model only handles judgment inside each step
use code for what code is good at use models for what models are good at
that’s the whole idea
Similar Articles
@lateinteraction: Claude Code is finally an RLM (oct 2025), congrats to Anthropic :-)
Claude Code's research preview now includes dynamic workflows, allowing Claude to write orchestration scripts and spin up coordinated subagents for complex tasks.
@unicodef1wn: https://x.com/unicodef1wn/status/2070179071548395916
A thread explaining how Anthropic's dynamic workflows in Claude Code allow Claude to build custom harnesses for complex tasks, preventing failure modes like agentic laziness, self-preferential bias, and goal drift by splitting work across separate agents. It includes practical examples and patterns for users to implement.
An article detailing the exact configuration and workflows that Anthropic's own engineers use with Claude Code, including parallel instances, CLAUDE.md patterns, writer/reviewer separation, skills fol
An article detailing the exact configuration and workflows that Anthropic's own engineers use with Claude Code, including parallel instances, CLAUDE.md patterns, writer/reviewer separation, skills folders, plugins, hooks, and batch operations.
@PrajwalTomar_: You don't understand how BIG this is. Anthropic just published the 4 ways to make Claude Code work without you. Everyon…
Anthropic published four types of loops for Claude Code to operate autonomously: turn-based, goal-based, time-based, and proactive, allowing different levels of task handoff.
@FinanceYF5: Source:
Claude Code introduces a dynamic workflow feature where Claude writes orchestration scripts, spawns subagent swarms, and verifies results, accessible via /model opus 4.8 and /effort ultracode.