Anthropic just launched Claude Opus 4.8. Also, there two Claude Code updates shipped with it. Dynamic workflows run many subagents in parallel. Fast mode now supports Opus 4.8 at a lower price. Both are research previews.
What Dynamic Workflows Actually Are
A dynamic workflow is a JavaScript script that orchestrates subagents at scale. Claude writes the script for the task you describe. A runtime then executes it in the background. Your session stays responsive while agents work.
The plan moves into code, not Claude’s context window. Intermediate results live in script variables instead. So Claude’s context holds only the final answer. That is the core difference from subagents and skills.
The feature requires Claude Code v2.1.154 or later. It runs in the CLI, Desktop, and VS Code extension. It is available on Max, Team, and Enterprise plans. It is on by default on Max and Team. On Enterprise it is off until an admin enables it. It also runs on the Claude API, Amazon Bedrock, Vertex AI, and Microsoft Foundry.
You can start a workflow in two ways. Include the word workflow anywhere in your prompt. Or turn on a setting called ultracode. Ultracode combines xhigh reasoning effort with automatic workflow orchestration. Claude Code also bundles /deep-research as a built-in workflow.
How a Workflow Runs
When a workflow kicks off, Claude plans dynamically from your prompt. It breaks the task into subtasks. It fans work across subagents running in parallel. Agents address the problem from independent angles. Other agents then try to refute those findings. The run iterates until the answers converge. Results are checked before they are folded in.
The runtime applies hard limits. It allows up to 16 concurrent agents. It caps each run at 1,000 agents total. The workflow script itself cannot touch the filesystem or shell. Only the agents read, write, and run commands.
Progress is saved as the run proceeds. An interrupted job resumes within the same session. Completed agents return cached results on resume. Coordination happens outside the conversation, so the plan stays on track.
The Bun Rewrite Example
Anthropic highlighted one large example. Jarred Sumner used dynamic workflows to port Bun. The port moved Bun from Zig to Rust. It passed 99.8% of the existing test suite. It produced roughly 750,000 lines of Rust. It took eleven days from first commit to merge.
One workflow mapped the correct Rust lifetime for every struct field. The next wrote each .rs file as a behavior-identical port. Hundreds of agents worked in parallel, with two reviewers per file. A fix loop then drove the build and test suite until clean. The result is not yet in production.
What is Fast Mode Actually
Fast mode is not a different model. It is a high-speed configuration of Claude Opus. It delivers 2.5x faster output token speeds. Model intelligence and capabilities stay the same. You toggle it with /fast in Claude Code. A small ↯ icon marks an active session.
Fast mode trades cost for speed. For Opus 4.7 and 4.6, it is priced at $30/$150 per MTok. According to Anthropic official release, fast mode for Opus 4.8 is three times cheaper. It requires usage credits enabled on your account. It draws from those credits, not your plan’s included usage. It is best for rapid iteration and live debugging. Standard mode still fits long autonomous or cost-sensitive tasks.
Strengths and What to Watch
Strengths:
Workflows handle codebase-wide bug hunts, large migrations, and cross-checked research end-to-end.
Adversarial review and convergence aim for results a single pass cannot reach.
Fast mode keeps Opus-level quality while cutting latency for interactive work.
Resumable runs mean an interrupted workflow does not start over.
What to watch:
Both features consume meaningfully more tokens than a typical session.
A run can spawn up to 1,000 agents, so costs climb fast.
Fast mode bills from the first token at the higher rate.
Both ship as research previews, so pricing and availability may change.
Marktechpost’s Visual Explainer
@import url(‘https://fonts.googleapis.com/css2?family=Newsreader:ital,wght@0,400;0,500;0,600;1,500&family=Hanken+Grotesk:wght@400;500;600;700&family=JetBrains+Mono:wght@400;500&display=swap’);
#mtp-dwfm-guide{
–ink:#141413; –ink-soft:#39372f; –muted:#6b6862;
–cream:#f0eee6; –paper:#faf9f5; –clay:#cc785c; –clay-deep:#b5613f;
–line:#e4dfd2; –code-bg:#1f1e1d; –code-ink:#ece7da;
background:var(–cream)!important; color:var(–ink)!important;
font-family:’Hanken Grotesk’,-apple-system,sans-serif!important;
max-width:960px; margin:24px auto; padding:0;
-webkit-font-smoothing:antialiased; box-sizing:border-box;
border:1px solid var(–line)!important; border-radius:18px; overflow:hidden;
}
#mtp-dwfm-guide *,#mtp-dwfm-guide *::before,#mtp-dwfm-guide *::after{box-sizing:border-box;}
#mtp-dwfm-guide hr,#mtp-dwfm-guide p:empty,#mtp-dwfm-guide del,#mtp-dwfm-guide s{display:none!important;}
#mtp-dwfm-guide .mtp-bar{height:3px!important; width:100%; background:var(–line)!important;}
#mtp-dwfm-guide .mtp-bar span{display:block; height:3px!important; width:10%;
background:var(–clay)!important; transition:width .45s cubic-bezier(.4,0,.2,1);}
#mtp-dwfm-guide .mtp-viewport{overflow:hidden; background:var(–paper)!important;}
#mtp-dwfm-guide .mtp-track{display:flex; transition:transform .55s cubic-bezier(.45,.02,.18,1);}
#mtp-dwfm-guide .mtp-slide{min-width:100%; padding:clamp(30px,5vw,60px);
min-height:430px; display:flex; flex-direction:column; justify-content:center;}
#mtp-dwfm-guide .mtp-kick{font-family:’JetBrains Mono’,monospace!important;
font-size:11px; letter-spacing:.22em; text-transform:uppercase;
color:var(–clay-deep)!important; margin:0 0 18px;}
#mtp-dwfm-guide h2.mtp-title{font-family:’Newsreader’,Georgia,serif!important;
font-weight:500; font-size:clamp(26px,4.4vw,40px); line-height:1.12;
letter-spacing:-.01em; color:var(–ink)!important; margin:0 0 16px;}
#mtp-dwfm-guide .mtp-sub{font-size:clamp(15px,2vw,18px); line-height:1.55;
color:var(–ink-soft)!important; margin:0; max-width:46ch;}
#mtp-dwfm-guide ul.mtp-list{list-style:none; margin:6px 0 0; padding:0;}
#mtp-dwfm-guide ul.mtp-list li{position:relative; padding:0 0 0 26px; margin:0 0 14px;
font-size:clamp(14.5px,1.9vw,17px); line-height:1.5; color:var(–ink-soft)!important;}
#mtp-dwfm-guide ul.mtp-list li::before{content:””; position:absolute; left:0; top:.62em;
width:9px; height:9px; border-radius:50%; background:transparent!important;
border:1.5px solid var(–clay)!important;}
#mtp-dwfm-guide ul.mtp-list li b{color:var(–ink)!important; font-weight:600;}
#mtp-dwfm-guide code{font-family:’JetBrains Mono’,monospace!important; font-size:.88em;
background:rgba(204,120,92,.12)!important; color:var(–clay-deep)!important;
padding:1px 6px; border-radius:5px;}
#mtp-dwfm-guide pre{background:var(–code-bg)!important; color:var(–code-ink)!important;
border:1px solid #2c2a27!important; border-radius:10px; padding:18px 20px; margin:18px 0 0;
overflow-x:auto; font-family:’JetBrains Mono’,monospace!important;
font-size:13px; line-height:1.7;}
#mtp-dwfm-guide pre code{background:transparent!important; color:var(–code-ink)!important;
padding:0; border:none!important;}
#mtp-dwfm-guide pre .cmt{color:#8a8579!important;}
#mtp-dwfm-guide pre .cmd{color:#e0a07f!important;}
#mtp-dwfm-guide .mtp-stat{display:flex; flex-wrap:wrap; gap:10px 30px; margin:8px 0 6px;}
#mtp-dwfm-guide .mtp-stat .num{font-family:’Newsreader’,serif!important; font-weight:600;
font-size:clamp(24px,3.6vw,34px); color:var(–clay-deep)!important; line-height:1; display:block;}
#mtp-dwfm-guide .mtp-stat .lab{font-size:12.5px; color:var(–muted)!important; margin-top:6px; display:block;}
#mtp-dwfm-guide .mtp-cover .mtp-mark{font-family:’JetBrains Mono’,monospace!important;
font-size:12px; letter-spacing:.18em; color:var(–muted)!important;
text-transform:uppercase; margin-top:30px;}
#mtp-dwfm-guide .mtp-nav{display:flex; align-items:center; gap:16px;
padding:16px 24px; background:var(–cream)!important; border-top:1px solid var(–line)!important;}
#mtp-dwfm-guide .mtp-dots{display:flex; gap:9px; flex:1; flex-wrap:wrap;}
#mtp-dwfm-guide .mtp-dots button{width:8px; height:8px; padding:0; border-radius:50%;
border:none!important; background:#cfc9ba!important; cursor:pointer;
transition:transform .25s,background .25s;}
#mtp-dwfm-guide .mtp-dots button.on{background:var(–clay)!important; transform:scale(1.45);}
#mtp-dwfm-guide .mtp-counter{font-family:’JetBrains Mono’,monospace!important;
font-size:12px; color:var(–muted)!important; letter-spacing:.05em; min-width:54px; text-align:right;}
#mtp-dwfm-guide .mtp-counter .cur{color:var(–ink)!important;}
#mtp-dwfm-guide .mtp-arrows{display:flex; gap:8px;}
#mtp-dwfm-guide .mtp-arrows button{width:38px; height:38px; border-radius:50%;
border:1px solid var(–line)!important; background:var(–paper)!important; color:var(–ink)!important;
cursor:pointer; font-size:16px; line-height:1; display:flex; align-items:center; justify-content:center;
transition:background .2s,border-color .2s,color .2s;}
#mtp-dwfm-guide .mtp-arrows button:hover{background:var(–clay)!important;
border-color:var(–clay)!important; color:#fff!important;}
#mtp-dwfm-guide .reveal{opacity:0; transform:translateY(12px);}
#mtp-dwfm-guide .mtp-slide.is-active .reveal{animation:mtpRise .55s cubic-bezier(.2,.7,.3,1) forwards;}
#mtp-dwfm-guide .mtp-slide.is-active .reveal:nth-child(1){animation-delay:.05s;}
#mtp-dwfm-guide .mtp-slide.is-active .reveal:nth-child(2){animation-delay:.12s;}
#mtp-dwfm-guide .mtp-slide.is-active .reveal:nth-child(3){animation-delay:.19s;}
#mtp-dwfm-guide .mtp-slide.is-active .reveal:nth-child(4){animation-delay:.26s;}
#mtp-dwfm-guide .mtp-slide.is-active .reveal:nth-child(5){animation-delay:.33s;}
@keyframes mtpRise{to{opacity:1; transform:translateY(0);}}
@media (max-width:640px){
#mtp-dwfm-guide{margin:14px auto; border-radius:14px;}
#mtp-dwfm-guide .mtp-slide{padding:26px 22px; min-height:400px;}
#mtp-dwfm-guide pre{font-size:12px; padding:14px 14px; overflow-x:auto;}
#mtp-dwfm-guide .mtp-nav{padding:13px 16px; gap:10px;}
#mtp-dwfm-guide .mtp-arrows button{width:34px; height:34px;}
#mtp-dwfm-guide .mtp-stat{gap:8px 20px;}
#mtp-dwfm-guide .mtp-counter{min-width:46px;}
}
Claude Code · Practical Guide
Dynamic Workflows & Fast Mode in Claude Opus 4.8
What Anthropic launched on May 28, 2026, and how to use it. Written for early-level AI engineers, software engineers, and data scientists.
Marktechpost
01 · What launched
Two Claude Code updates, shipped with Opus 4.8
Anthropic released Claude Opus 4.8 on May 28, 2026.
Dynamic workflows run many subagents in parallel inside Claude Code.
Fast mode now supports Opus 4.8 at a lower price.
Both ship as research previews.
02 · The concept
What a dynamic workflow actually is
A JavaScript script that orchestrates subagents at scale.
Claude writes the script for the task you describe.
A runtime executes it in the background while your session stays responsive.
The plan lives in script variables, not Claude’s context window.
Only the final answer returns to your session.
03 · Mechanics
How a workflow runs
Claude plans dynamically from your prompt and breaks it into subtasks.
Subagents run in parallel, addressing the problem from independent angles.
Other agents then try to refute those findings.
The run iterates until the answers converge.
Results are verified before anything reaches you.
04 · Limits & access
The hard limits and where it runs
Up to 16 concurrent agents, and 1,000 agents total per run.
The script cannot touch the filesystem or shell; only agents do.
Progress is saved; an interrupted run resumes in the same session.
On by default on Max and Team; Enterprise needs an admin.
Requires Claude Code v2.1.154 or later.
05 · Getting started
Three ways to start a workflow
Include the word workflow anywhere in your prompt.
Turn on ultracode, which sets xhigh effort plus auto orchestration.
Run the bundled /deep-research workflow.
# 1. Trigger a workflow with the keyword
Run a workflow to audit every API endpoint under src/routes/ for missing auth checks
# 2. Let Claude decide when to use one
/effort ultracode
# 3. Use the built-in research workflow
/deep-research What changed in the Node.js permission model between v20 and v22?
06 · In practice
The Bun rewrite example
99.8%existing test suite passing
~750Klines of Rust produced
11 daysfirst commit to merge
Jarred Sumner used dynamic workflows to port Bun from Zig to Rust.
Hundreds of agents ran in parallel, with two reviewers per file.
The result is not yet in production.
07 · Fast mode
Same Opus, faster output
Not a different model; a high-speed configuration of Claude Opus.
2.5x faster output token speeds at identical quality.
Toggle with /fast; a ↯ icon marks it active.
$30 / $150 per MTok on 4.7 and 4.6; three times cheaper for Opus 4.8.
Requires usage credits; best for rapid iteration and live debugging.
08 · Decision
Which one to reach for
Use a workflow when one conversation cannot coordinate the agents.
Use fast mode when latency matters more than cost.
Both consume meaningfully more usage than a typical session.
Start scoped, watch usage, and verify outputs before trusting long runs.
09 · Sources
Read the primary docs
Anthropic — Introducing Claude Opus 4.8
Claude — Introducing dynamic workflows in Claude Code
Claude Code docs — Orchestrate subagents at scale with dynamic workflows
Claude Code docs — Speed up responses with fast mode
Marktechpost · AI engineering coverage
01 / 10
←
→
(function(){
var root=document.getElementById(‘mtp-dwfm-guide’);
if(!root||root.dataset.init)return; root.dataset.init=1;
var track=root.querySelector(‘.mtp-track’);
var slides=root.querySelectorAll(‘.mtp-slide’);
var dots=root.querySelector(‘.mtp-dots’);
var prev=root.querySelector(‘.mtp-prev’);
var next=root.querySelector(‘.mtp-next’);
var cur=root.querySelector(‘.mtp-counter .cur’);
var bar=root.querySelector(‘.mtp-bar span’);
var i=0, n=slides.length;
for(var d=0; d