wf-new

wf-new is a command for coding agents from hesreallyhim/ultracode-workflows. It costs 20 tokens per session (417 once invoked), scanned A, original, MIT.

A command for creating a reusable ultracode Workflow script from a task description. A workflow is a defined sequence in which multiple AI agents can work, review, or verify a task.

In plain words
What is it for?
Use it to design new workflow scripts, choose an orchestration structure, set cost or time preferences, and review the result without running it.
Why use it?
It helps decide whether a recurring task needs a multi-agent workflow and shapes the workflow before writing it.

Command

Part of the ultracode-workflows plugin — 1 skill, 7 commands, 1 hook shipped together

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/hesreallyhim/ultracode-workflows/wf-new
Clone the repo
git clone --depth 1 https://github.com/hesreallyhim/ultracode-workflows

Or install ultracode-workflows, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for wf-new

README.md
[![agentmods](https://agentmods.dev/badge/commands/hesreallyhim/ultracode-workflows/wf-new.svg)](https://agentmods.dev/commands/hesreallyhim/ultracode-workflows/wf-new)
Your own site
<a href="https://agentmods.dev/commands/hesreallyhim/ultracode-workflows/wf-new"><img src="https://agentmods.dev/badge/commands/hesreallyhim/ultracode-workflows/wf-new.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 417 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 $0.00020 $0.00417
Opus 5 $0.00010 $0.00209
Sonnet 5 $0.00004 $0.00083
Haiku 4.5 $0.00002 $0.00042

Measured 3d ago against content hash 3b34b9fad311, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wf-new 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 3d 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.

plugins/ultracode-workflows/commands/wf-new.md · 22 lines

What it actually says

/wf-new

The user wants a new Workflow script for: $ARGUMENTS

Invoke the workflow-authoring skill as a pattern composer and follow its procedure end to end:

  1. Decide whether the task warrants a reusable multi-agent workflow; recommend a simpler prompt when it does not.
  2. Show a compact orchestration brief, one recommended catalog composition, and at most two meaningful alternatives. Offer quick/balanced/deep cost presets, let the user override their individual levers, and identify whether token ceiling or duration target wins when both are tight. Include agent-count, peak-width, sequential-depth, budget-guard, and duration assumptions; explain which figures are exact, ranged, or unknown.
  3. Select two or three nearest marketplace workflows as structural, trust, and scale precedents. Extract their invariants rather than copying their agent counts or phase names.
  4. Design the structured dataflow, failure meanings, convergence/coverage rule, and mutation boundary before writing prompts.
  5. Draft the smallest topology that preserves those invariants, consulting the skill's API-contract reference only for harness details.
  6. Review the completed source without executing it. In this repository checkout, run the repository parser gate against the actual authored path, not the default catalog command.
  7. Generate an advisory static terminal diagram, relay it inside a fenced plain-text code block, explain the visible composition patterns and exact/ranged/unknown widths, and offer one focused revision pass before delivery.
  8. Save the script to this project's .claude/workflows/<name>.js (create the directory if needed) and tell the user how to invoke it, which catalog patterns informed it, and what remains uncertain.

If $ARGUMENTS is empty, ask the user what the workflow should accomplish before starting.

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. 3d ago First seen · 22 lines · 20 tokens per session scan A 3b34b9fad311

Subscribe to this mod's changes

wf-new is a command published in the GitHub repository hesreallyhim/ultracode-workflows (2 stars, last pushed 27d ago), licensed MIT. It adds 20 tokens to every session and 417 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 2026-08-31.