Skip to content

Claude Code — workflows ​

Advanced Dynamic workflows, fan-out, verification, and how ultracode orchestrates them (2026).

Parent map: Claude Code 2026.

Official: Orchestrate subagents at scale with dynamic workflows

What is a dynamic workflow? ​

Instead of you manually spawning every worker, Claude can:

  1. Plan a multi-step approach for a substantive task
  2. Fan out work to subagents (sometimes many)
  3. Collect results
  4. Optionally grade / revise (performance outcomes — worker revises until a rubric is met)

Anthropic’s 2026 direction: lead agent plans dynamically and can scale parallel subagents in one session, with stronger verification loops.

Ultracode ↔ workflows ​

Ultracode is a Claude Code effort setting, not a separate binary:

  • Sends xhigh reasoning effort to the model
  • Turns on automatic workflow orchestration for substantive tasks
bash
# Start a session already in ultracode
claude --effort ultracode

# Inside a session
/effort ultracode

One-shot workflow without changing session effort (keyword in the prompt):

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

Explicit orchestration:

text
create a workflow that migrates every internal fetch() call to the new HttpClient wrapper

use a workflow to migrate every component under src/components/ from styled-components to Tailwind,
working on each file in its own isolated copy

With ultracode on, one user request may become several workflows in a row (understand → change → verify). That uses more tokens and time than /effort high.

Drop back:

text
/effort high

Requires a recent CLI (docs cite v2.1.203+ for ultracode) and a model that supports xhigh effort. Confirm with your claude --version and model config.

Details: claude-code-ultra.

Common workflow shapes ​

1. Explore → Plan → Execute → Verify ​

text
Explore:  read-only subagents map modules
Plan:     /plan or plan permission mode; you approve
Execute:  implement on a branch / worktree
Verify:   tests + /code-review (+ optional second agent)

2. Fan-out by area ​

text
Lead: "Dynamic workflow: implement feature X.
       Parallelize independent files; one worker per area;
       return diffs only; main session integrates."

3. Batch across the codebase ​

text
/batch

Decomposes a large change into independent units; often pairs with worktrees.

4. Graded workers (when available) ​

Lead defines success criteria; each subagent result is scored; failures revise until they pass — fewer silent half-done workers. See workflows docs for current “performance outcomes” behavior.

Settings & scale (high level) ​

Production setups in mid-2026 often combine:

KnobRole
Fallback model chainsSurvive overloads
Nested subagentsDepth of delegation (can get expensive)
Max parallel workersCap fan-out
HooksSubagentStop, permission gates
CLAUDE.md rulesWhen to workflow vs stay single-threaded

Prefer project settings + documented rules over ad-hoc “spin 50 agents.”

Example shape (illustrative — keys change; verify against settings):

json
{
  "permissions": {
    "defaultMode": "acceptEdits"
  }
}

Use official docs for nested-agent depth, concurrency caps, and fallback chains — wrong configs can burn quotas quickly.

Everyday vs workflow mode ​

RoutineSubstantive
Typo, one-file fixFeature spanning many files
Quick questionUnfamiliar subsystem
/effort high or default/effort ultracode or explicit workflow prompt
Single sessionExplore + plan + parallel execute

Cost discipline ​

  1. Cap concurrent workers
  2. Prefer short summaries from workers
  3. Use /cost and account dashboards
  4. Ultracode = session-scoped; reset for small tasks
  5. Don’t combine ultracode + max parallelism + cloud ultra review unless needed