Skip to content
Dynamic Workflows in Claude Code: A Complete Guide to Multi-Agent Harnesses

The Trove library · other

Dynamic Workflows in Claude Code: A Complete Guide to Multi-Agent Harnesses

By Research compilation — Anthropic blog + Claude Code documentation

Complete reference for Claude Code's dynamic workflows feature. Covers the JavaScript orchestration model, six workflow patterns (classify-and-act, fan-out-and-synthesize, adversarial verification, generate-and-filter, tournament, loop-until-done), all major use cases (migrations, research, verification, triage, evals, model routing), prompting strategies, token budgets, and saving/sharing workflows. Based on Anthropic's official blog post by Thariq Shihipar and Sid Bidasaria.

  • 40 pages
  • 40 chapters
  • Updated September 7, 2026

Free to add

Read a preview
Use with your AI agent

Add the book to your library, then connect Trove to the AI tool you use.

See installation options

A look inside · First page

Dynamic Workflows in Claude Code: A Complete Guide to Multi-Agent Harnesses

Load this book when:

  • You are deciding whether a task should run as a Claude Code dynamic workflow instead of a single turn.
  • You are choosing which of the six core workflow patterns (classify-and-act, fan-out-and-synthesize, adversarial verification, generate-and-filter, tournament, loop-until-done) fits a task.
  • You are diagnosing agentic laziness, self-preferential bias, or goal drift in a long or parallel task.
  • You are wiring ultracode, /goal, or /loop into a workflow and need the exact trigger and stop-condition mechanics.
  • You are routing subtasks across Haiku/Sonnet/Opus or setting a token budget for an orchestration.
  • You want to understand Loop Engineering — designing systems that prompt agents, not prompting agents yourself.
  • You need to build a durable agent loop with automations, worktrees, skills, sub-agents, and memory.
  • You are choosing between a dynamic workflow (Claude writes the JS) and a deterministic workflow (you write it once and commit it).
  • You need a multi-hour job (bulk API pull, large scrape, long batch export) to survive session restarts, background-task kills, and an absent user.

Author: Research compilation — Anthropic blog + Claude Code documentation + community research (Addy Osmani, Forward Future Loop Library, Boris Cherny) Source: "A harness for every task" — Anthropic Blog, 2026 (Thariq Shihipar & Sid Bidasaria); "Loop Engineering" — Addy Osmani, June 2026; Forward Future Loop Library, June 2026 Target: Claude Code users who want to orchestrate multi-agent workflows for complex tasks Last updated: 2026-08-22 Audience & governance: Marketplace (public) reference book — optimize for circulation and attribution (per Writing Books for AI Agents, Ch 13). Valid as of: 2026-06-19, Claude Code v2.1.154+ (dynamic workflows GA). Refresh cadence: review every release that bumps subagent caps, model lineup, or the /goal//loop/ultracode surface (tactical/volatile domain — short cadence).


Add this book to your library to keep reading.

What’s inside

01Dynamic Workflows in Claude Code: A Complete Guide to Multi-Agent Harnessesp. 1
02Chapter 0 — Scope & Currencyp. 2
03Chapter 1 — The Problem Workflows Solvep. 3
04Chapter 2 — Decision Matrixp. 4
05Chapter 3 — Dynamic vs Static Workflowsp. 5

13Chapter 11 — Migrations and Refactorsp. 13
14Chapter 12 — Deep Researchp. 14
15Chapter 13 — Deep Verificationp. 15
16Chapter 14 — Sorting at Scalep. 16
17Chapter 15 — Memory and Rule Adherencep. 17
18Chapter 16 — Root-Cause Investigationp. 18
19Chapter 17 — Triaging at Scalep. 19
20Chapter 18 — Exploration and Tastep. 20
21Chapter 19 — Evalsp. 21

23Chapter 21 — Triggering Workflowsp. 23
24Chapter 22 — Prompting Strategiesp. 24
25Chapter 23 — Token Budgetsp. 25
26Chapter 24 — Saving and Sharing Workflowsp. 26

28Chapter 26 — Pattern Selection Guidep. 28
29Chapter 27 — Use Case Quick Referencep. 29
30Chapter 28 — Failure Mode Referencep. 30
31Chapter 29 — Example Prompt Galleryp. 31

36Chapter 34 — Loop Maturity Ladderp. 36

About this book

Complete reference for Claude Code's dynamic workflows feature. Covers the JavaScript orchestration model, six workflow patterns (classify-and-act, fan-out-and-synthesize, adversarial verification, generate-and-filter, tournament, loop-until-done), all major use cases (migrations, research, verification, triage, evals, model routing), prompting strategies, token budgets, and saving/sharing workflows. Based on Anthropic's official blog post by Thariq Shihipar and Sid Bidasaria.