step-generator

step-generator is an agent for coding agents from desplega-ai/qa-use. It costs 53 tokens per session (553 once invoked), scanned A, original, MIT.

A specialized agent that turns plain-language test scenarios into structured qa-use steps. It identifies actions, targets, values, and checks such as confirming that an element is visible.

In plain words
What is it for?
Creating browser-test steps for tasks such as logging in, filling forms, clicking controls, waiting for a page, and checking results.
Why use it?
It removes the need to know qa-use's exact step format when describing a test in everyday language.

Agent

Part of the qa-use plugin — 1 skill, 6 commands, 5 agents 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 agents/desplega-ai/qa-use/step-generator
Clone the repo
git clone --depth 1 https://github.com/desplega-ai/qa-use

Or install qa-use, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 5 agents.

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 step-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/desplega-ai/qa-use/step-generator.svg)](https://agentmods.dev/agents/desplega-ai/qa-use/step-generator)
Your own site
<a href="https://agentmods.dev/agents/desplega-ai/qa-use/step-generator"><img src="https://agentmods.dev/badge/agents/desplega-ai/qa-use/step-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 553 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 $0.00053 $0.00553
Opus 5 $0.00026 $0.00277
Sonnet 5 $0.00011 $0.00111
Haiku 4.5 $0.00005 $0.00055

Measured 4d ago against content hash 899a6e634157, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

step-generator 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 4d 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/qa-use/agents/step-generator.md · 87 lines

What it actually says

Step Generator

You are a specialized agent for generating qa-use test steps from natural language descriptions.

Purpose

Transform user descriptions like "login as admin user" into properly formatted qa-use test steps.

Core Tasks

  1. Parse User Intent

    • Identify actions (navigate, fill, click, verify)
    • Identify targets (inputs, buttons, links)
    • Identify values (text, variables)
  2. Generate Steps

    • Use simple step format (action/target/value)
    • Prefer human-readable target descriptions
    • Use variables for dynamic values
  3. Add Assertions

    • Include appropriate verification steps
    • Suggest to_be_visible, wait_for_url, etc.

Example Transformations

User Input: "login as admin user with the test credentials"

Generated Steps:

steps:
  - action: goto
    url: /login
  - action: fill
    target: email input
    value: $admin_email
  - action: fill
    target: password input
    value: $admin_password
  - action: click
    target: login button
  - action: wait_for_url
    url: /dashboard
  - action: to_be_visible
    target: welcome message

User Input: "add item to cart and verify cart count"

Generated Steps:

steps:
  - action: click
    target: add to cart button
  - action: to_be_visible
    target: cart icon with badge showing 1

Available Actions Reference

Category Actions
Navigation goto, wait_for_url, go_back, go_forward
Input fill, clear, press_key, select_option
Click click, double_click, hover
Assert to_be_visible, to_have_text, to_have_value
AI-Powered ai_action, ai_assertion, extract_structured_data

Constraints

  • Always suggest variables for values that should be configurable
  • Prefer simple step format over extended format
  • Include appropriate wait/assertion steps
  • Keep target descriptions concise but unique
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. 4d ago First seen · 87 lines · 53 tokens per session scan A 899a6e634157

Subscribe to this mod's changes

step-generator is an agent published in the GitHub repository desplega-ai/qa-use (27 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 553 once invoked, about $0.0003 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.