# Workflows: a script for many agents

Course: Claude Code: Pro Level — https://zero2vibecode.com/learn/claude-code-pro
Canonical URL: https://zero2vibecode.com/learn/claude-code-pro/4-3-dynamic-workflows
Verified against: Claude Code v2.1.292 (2026-10-15)
Last updated: 2026-10-15

A dynamic workflow is a JavaScript script Claude writes for the task. The script launches agents and keeps their results to itself, and only the final result reaches the conversation. You can read the plan before it runs and save a good run as a /<name> command.

In the last lesson you chose a pattern. If the task needs many agents, double-checked findings or reruns, that is a dynamic workflow.

## What it is

A workflow is a JavaScript script that Claude writes for your task. The script runs in the background, and your session stays responsive. It launches subagents itself and keeps their results in its own variables, and only the final result reaches the conversation. The script holds the plan, not Claude.

Since the plan is code, you can:

- read it **before** it runs;
- make independent agents verify each other's findings;
- save it and run it again as a `/<name>` command.

On the Pro plan, workflows are off until you turn on the **Dynamic workflows** row in `/config`.

## How to ask

Just say the word "workflow" in your request:

```text
use a workflow to audit every file under src/ for errors that are caught and then ignored, and adversarially verify each finding before reporting it
```

There is also a built-in workflow, `/deep-research` — research with web search.

Before running, Claude Code shows the plan's phases and asks: **Yes, run it**, **View raw script** or **No**. Choose **View raw script** or press `Ctrl+G` to open the script in your editor. In manual mode, Claude Code asks before every run — so you see every plan before it starts.

## What a script looks like

```javascript
export const meta = {
  name: 'audit-routes',
  description: 'Audit every route handler for missing auth checks',
}

const found = await agent('List every .ts file under src/routes/.', {
  schema: { type: 'object', required: ['files'], properties: { files: { type: 'array', items: { type: 'string' } } } },
})

const audits = await pipeline(found.files, file =>
  agent(`Audit ${file} for missing authentication checks.`, { label: file }),
)

return audits.filter(Boolean)
```

- `agent()` launches one subagent;
- `pipeline()` launches one agent per item in a list;
- `parallel()` launches a set of agents at once;
- `args` is the input you pass to a saved workflow.

The first statement is always `export const meta`: a plain object literal with `name` and `description`. If a variable, a function call or a spread gets in there, the `/<name>` command disappears from autocomplete.

## The /workflows panel

While a workflow is running, type `/workflows` and pick the run:

| Key | What it does |
|---|---|
| `↑` `↓` | select a phase or an agent |
| `Enter` | open a phase, then an agent: prompt, calls, result |
| `Esc` | back |
| `p` | pause and resume |
| `x` | stop the run |
| `s` | save the script |

When saving, `Tab` switches the location: `.claude/workflows/` in the project is shared with everyone who clones the repository once you commit it; `~/.claude/workflows/` is yours alone, but in every project. From the next session, the saved script runs as `/<name>` and takes input, for example: `Run /todo-audit on src`.

## The size of a run

```text
/config workflowSizeGuideline=small
```

`small` asks Claude to plan as few agents as possible. The setting is stored in `~/.claude.json`, not in the repository, and applies from the next request. It is **guidance**, not a limit. If a run grows large, a `Large workflow` warning appears in the progress line, but it neither pauses nor limits the run. To save money, start the session with `--model sonnet`: unless something else sets the model, workflow agents run on the session's model.

A run stopped with `x` does not resume with `p`: ask Claude to rerun the same script.

**Careful.** 
In auto mode, Claude Code asks only before the very first workflow run: any "Yes" records consent in your user settings, and later runs start without a question. Workflow agents follow your permission rules, and in accept-edits, auto and bypass modes they run in the same mode. Read every script before approving it, and stay in manual for a workflow you have not read yet. A run can cost noticeably more than the same task in a conversation — try it on one small folder first.

**Practice in the terminal.** Create .claude/workflows/todo-audit.js: the first line is export const meta with name and description, the second is return await agent(...) with the folder from args spliced in. In a real project you would usually save a script like this with s in /workflows and then edit it.