Ultracode: Claude Code Multi-Agent Orchestration Mode Explained

Last updated: June 11, 2026

If you typed the word "workflow" into Claude Code in late May and watched it spin up a background orchestration run, then tried the same thing this week and got nothing, you hit a deliberate rename. As of v2.1.160, the trigger keyword for dynamic workflows is ultracode, and the same name also appears in the /effort menu. Two different behaviors share one name, which is exactly why search results about it are confusing.

This post explains both, using only what the Claude Code changelog and the official docs actually say, verified on June 11, 2026. For the full mechanics of workflow scripts themselves, see the dynamic workflows guide. This post is about the ultracode entry points specifically.

What Ultracode Actually Is: Two Documented Behaviors

Dynamic workflows shipped in Claude Code v2.1.154. A workflow is a JavaScript orchestration script that Claude writes for your task and a runtime executes in the background, across what the announcement post describes as tens to hundreds of parallel subagents. Intermediate results live in script variables rather than in Claude's context window, which is what lets a run scale past what one conversation can coordinate.

Ultracode is how you reach that machinery. The workflows documentation describes two distinct entry points.

The prompt keyword: one task, one workflow

Include the literal keyword ultracode anywhere in a prompt and Claude writes a workflow script for that task instead of working through it turn by turn:

ultracode: audit every API endpoint under src/routes/ for missing auth checks

The keyword is highlighted in the prompt input - violet, per the v2.1.160 changelog - so you can see the trigger armed before you hit Enter. Three documented escape hatches exist if you typed it by accident:

• Press Option+W on macOS or Alt+W on Windows and Linux to dismiss the highlight for that prompt
• Press backspace while the cursor sits right after the highlighted keyword
• Turn off "Ultracode keyword trigger" in /config to disable keyword detection entirely

Asking in your own words, for example "use a workflow for this", still works in every version; the docs treat a direct natural-language request as the same opt-in. The rename only retired the literal workflow keyword as a trigger: per the changelog, the word "workflow" no longer starts a run on its own.

The /effort setting: Claude decides per task

The second behavior is a session setting:

/effort ultracode

The model configuration docs define it precisely: "Ultracode is a Claude Code setting rather than a model effort level: it sends xhigh to the model and additionally has Claude orchestrate dynamic workflows for substantive tasks."

That sentence settles the most common misconception: the API never receives an effort value called ultracode. The model runs at xhigh, and Claude Code layers automatic orchestration on top. With the setting on, Claude plans a workflow for each substantive task without waiting for the keyword. The docs note that a single request can turn into several workflows in a row: one to understand the code, one to make the change, one to verify it.

Ultracode applies to the current session only and resets when you start a new one. It is deliberately excluded from every persistence mechanism: the docs state it is not part of the effortLevel setting, the --effort flag, or the CLAUDE_CODE_EFFORT_LEVEL environment variable. The two documented programmatic routes are --settings and an Agent SDK control request:

claude --settings '{"ultracode": true}'

That session-only design is a cost guardrail: multi-agent runs on every substantive task are expensive by construction, and the docs recommend dropping back with /effort high for routine work.

Ultracode vs Ultrathink vs xhigh

Three similar-sounding controls do three different jobs, all documented on the model configuration page:

A useful mental model: ultrathink makes one response think harder, xhigh makes every response think harder, and ultracode makes the harness work differently - it moves execution out of the conversation and into orchestrated background agents.

Model support follows the effort ladder. Per the model configuration docs, xhigh is available on Fable 5, Opus 4.8, and Opus 4.7, but not on Opus 4.6 or Sonnet 4.6, where the ladder tops out at high and max. Ultracode is only offered on models that support xhigh; on other models the /effort menu simply does not show it. That behavior was tightened in v2.1.160, whose changelog notes a fix for /effort ultracode "incorrectly blaming the dynamic workflows setting when the model cannot run xhigh." If you want the full ladder including where max fits and why the same level name maps to different underlying values per model, see Fable 5 effort levels explained.

What Happens When a Workflow Triggers

Whichever entry point you use, the run behaves the same way, and the limits are documented:

• Up to 16 concurrent agents, fewer on machines with limited CPU cores
• 1,000 agents total per run, which bounds the cost of a runaway script
• No mid-run user input; only agent permission prompts can pause a run
• The script itself has no filesystem or shell access; agents do the reading, writing, and command running

You watch and manage runs with /workflows: drill into phases and individual agents, see token totals per agent, pause and resume with p, stop with x, restart an agent with r, and save the run's script as a reusable command with s. Saved scripts land in .claude/workflows/ for the project or ~/.claude/workflows/ for your user, and run as /<name> afterward. A saved workflow accepts structured input through an args global:

> Run /triage-issues on issues 1024, 1025, and 1030

Claude passes the list as structured data, so the script can call array methods on args directly. This save-and-rerun loop is the practical payoff for repeated jobs: trigger a run once with the keyword, confirm it does what you want, press s, and the orchestration becomes a versionable artifact your whole team can run. For how workflows compare against subagents and agent teams as coordination primitives, see the subagents vs agent teams vs workflows breakdown.

Separately from workflows, v2.1.172 allows sub-agents to spawn their own sub-agents up to 5 levels deep - worth knowing when you reason about how much parallel machinery a single prompt can now mobilize.

Permissions and Cost: Check Before a Long Run

Two operational details from the workflows docs matter before you leave an ultracode session running.

First, permissions. Workflow subagents always run in acceptEdits mode and inherit your tool allowlist regardless of your session's permission mode. File edits are auto-approved. Shell commands, web fetches, and MCP tools outside your allowlist can still prompt you mid-run, so the docs recommend adding the commands agents will need to your allowlist before starting a long run. Note also that in auto mode the launch approval prompt is skipped entirely when ultracode is on - convenient, but it removes the last launch checkpoint, leaving only non-allowlisted tool calls to pause a run.

Second, cost. Runs count toward your plan's usage and rate limits like any other session, and every agent uses your session's model unless the script routes a stage to a different one. The docs' advice is to gauge spend on a small slice first: one directory instead of the whole repo. With /effort ultracode active this compounds, because every substantive task in the session pays the orchestration premium. If you are running multiple sessions of this kind, the operational patterns in managing a fleet of Claude agents apply directly, and the orchestrator model playbook covers routing cheap stages to cheap models.

Turning It Off, and Version Requirements

Requirements, all from the workflows docs: Claude Code v2.1.154 or later, on any paid plan, the Anthropic API, Bedrock, Vertex AI, or Microsoft Foundry. Pro users enable workflows from the Dynamic workflows row in /config. The keyword has been spelled ultracode since v2.1.160.

Three documented ways to disable workflows for yourself:

// ~/.claude/settings.json
{ "disableWorkflows": true }

Or toggle Dynamic workflows off in /config, or set CLAUDE_CODE_DISABLE_WORKFLOWS=1 in your environment. When workflows are disabled, the ultracode keyword stops triggering and ultracode disappears from the /effort menu. Organizations can set disableWorkflows in managed settings. If you only dislike the keyword but want workflows available on request, the narrower "Ultracode keyword trigger" toggle in /config is the right knob.

One honest caveat to close on: most tasks do not need a workflow. The docs position them for jobs that need more agents than one conversation can coordinate - codebase-wide audits, large migrations, cross-checked research. For everything else, /effort high and a normal conversation remain the cheaper, faster, easier-to-review path.

FAQ

What does ultracode do in Claude Code?

Two things, depending on where you use it. As a keyword in a prompt, it runs that single task as a dynamic workflow - a background orchestration script coordinating up to 16 concurrent subagents - without changing your session settings. As /effort ultracode, it sets reasoning effort to xhigh and has Claude automatically plan workflows for every substantive task in the session.

Is ultracode an effort level like xhigh or max?

No. The model configuration docs state it is "a Claude Code setting rather than a model effort level." The model itself runs at xhigh; the ultracode part is harness behavior, which is why it cannot be set through effortLevel, --effort, or CLAUDE_CODE_EFFORT_LEVEL, and why it resets when the session ends.

What is the difference between ultracode and ultrathink?

ultrathink is a prompt keyword that requests deeper reasoning on one turn by adding an in-context instruction; the effort level sent to the API does not change and no extra agents run. ultracode triggers multi-agent workflow orchestration. They solve different problems: ultrathink for one hard question, ultracode for one large task.

Which models support ultracode?

Models that support the xhigh effort level: Fable 5, Opus 4.8, and Opus 4.7 per the current model configuration docs. On Opus 4.6 and Sonnet 4.6 the /effort menu does not offer ultracode. Since v2.1.160, Claude Code hides the option rather than erroring when the model cannot run xhigh.

How do I stop the ultracode keyword from triggering workflows?

Per prompt: press Option+W (macOS) or Alt+W (Windows/Linux), or backspace immediately after the highlighted keyword. Permanently: turn off "Ultracode keyword trigger" in /config. To disable workflows entirely, set "disableWorkflows": true in settings or CLAUDE_CODE_DISABLE_WORKFLOWS=1 in your environment.

Sources

• Claude Code CHANGELOG.md - v2.1.154 (dynamic workflows introduction), v2.1.160 (keyword rename, ultracode fix), v2.1.172 (nested sub-agents). Accessed June 11, 2026.
• Orchestrate subagents at scale with dynamic workflows - Claude Code docs - keyword and /effort ultracode behavior, limits, permissions, /workflows controls, disable settings. Accessed June 11, 2026.
• Model configuration - Claude Code docs - effort level ladder per model, ultracode definition, ultrathink keyword, session-only behavior. Accessed June 11, 2026.
• Introducing dynamic workflows in Claude Code - Claude blog - announcement framing, use cases, availability. Accessed June 11, 2026.