create-workflow

A command that creates a custom workflow from a name and description. It generates a mode skill, which defines how the workflow operates, and a shortcut command to start it.

In plain words
What is it for?
It is for scaffolding project-specific workflows that users can run through a shortcut command.
Why use it?
It removes the need to create and connect those workflow files by hand.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/dheerg/swarms/create-workflow
Clone the repo
git clone --depth 1 https://github.com/DheerG/swarms
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,702 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00013 $0.05702
Opus 5 $0.00006 $0.02851
Sonnet 5 $0.00003 $0.01140
Haiku 4.5 $0.00001 $0.00570

Measured 2d ago against content hash 77ff2b2ca0c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/create-workflow.md · 415 lines

How it starts

The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/swarm:create-workflow

You are scaffolding a custom swarm workflow. This generates two files in the user's project:

  1. A mode skill (.claude/skills/<name>-mode/SKILL.md) — the domain-specific operational spec
  2. A shortcut command (.claude/commands/<name>.md) — the entry point users invoke

The interaction model is generate first, edit after. Ask the minimum needed to infer the full spec, generate everything, then let the user adjust.

Step 0: Gather

$ARGUMENTS

If $ARGUMENTS contains a name and description (has sentence structure, verbs, or a separator like write-article — takes raw thoughts and produces a polished blog post): extract both and proceed directly to Step 1.

If $ARGUMENTS appears to be a name only (kebab-case identifier, no verb or sentence structure — e.g., write-article): use it as the workflow name. Ask one question (plain text): "What does this workflow do? What does the user get at the end?" Wait for their response. Then proceed to Step 1.

If $ARGUMENTS is empty: ask one question (plain text): "What's this workflow called, and what does it do? (e.g., write-article — takes raw dictated thoughts and produces a polished blog post)" Wait for their response. Parse the name and purpose. Then proceed to Step 1.

Validate: the name should be kebab-case. If not, convert it silently.


Step 0.5: Determine Workflow Type

Before inferring the spec, decide whether this workflow should be a thin wrapper (extension of a built-in mode) or a full custom mode.

Infer the closest built-in mode from the purpose:

  • Writing / editing / documentation / narrative → swarm:writing-mode
  • Code / engineering / building / debugging → swarm:code-mode
  • Anything else (research, synthesis, evaluation) → swarm:general-mode

Use AskUserQuestion:

  • question: "How should this workflow be structured?"
  • header: "Type"
  • options:
    • label: "Thin wrapper over [inferred base] (Recommended)" description: "Inherits phase arc, lead identity, and facilitator from the base. You add intake (Pre-flight actions), an outcomes question, and additive Mode-Specific Rules + Suggest-Members Guidance. Stays in sync with swarm updates."
    • label: "Full custom mode" description: "Use when the workflow needs custom phase semantics, a distinct lead identity, or substantial domain governance. More surface to maintain; runs /swarm:update-workflow to stay current on wiring."
    • label: "Wrapper — pick a different base" description: "Create a thin wrapper but choose the base mode explicitly."

Read the full file on GitHub · 415 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 415 lines · 13 tokens per session scan A 77ff2b2ca0c0

Subscribe to this mod's changes

create-workflow is a command published in the GitHub repository DheerG/swarms (86 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 5,702 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.