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.
npx skills add aigentive/RalphX --skill qa-step-generationgit clone --depth 1 https://github.com/aigentive/RalphXWrote 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.
[](https://agentmods.dev/skills/aigentive/ralphx/qa-step-generation)<a href="https://agentmods.dev/skills/aigentive/ralphx/qa-step-generation"><img src="https://agentmods.dev/badge/skills/aigentive/ralphx/qa-step-generation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aigentive/ralphx/qa-step-generation"><img src="https://agentmods.dev/badge/skills/aigentive/ralphx/qa-step-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00014 | $0.01169 |
| Opus 5.5 | $0.00006 | $0.00468 |
| Sonnet 5.5 | $0.00003 | $0.00234 |
| Haiku 4.5 | $0.00001 | $0.00117 |
Grade A, and why
qa-step-generation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Step Generation
Guidelines for creating executable QA test steps using agent-browser.
Test Step Structure
Each test step maps to one or more acceptance criteria and contains:
- id: Unique identifier (QA1, QA2...)
- criteria_id: Links to acceptance criterion
- description: What the step verifies
- commands: Array of agent-browser commands
- expected: What success looks like
Output Format
{
"qa_steps": [
{
"id": "QA1",
"criteria_id": "AC1",
"description": "Verify task board renders with all columns",
"commands": [
"agent-browser open http://localhost:1420",
"agent-browser wait --load",
"agent-browser snapshot -i -c",
"agent-browser is visible [data-testid='task-board']",
"agent-browser screenshot \"$RALPHX_AGENT_SCREENSHOT_DIR/qa1-taskboard.png\""
],
"expected": "Task board visible with 7 columns"
}
]
}
Command Patterns
Standard Test Template
agent-browser open <url>
agent-browser wait --load
agent-browser snapshot -i -c
# verification commands
agent-browser screenshot "$RALPHX_AGENT_SCREENSHOT_DIR/<task>-<step>.png"
agent-browser close
Visibility Verification
agent-browser is visible [data-testid='element']
agent-browser is visible .class-name
agent-browser is visible #element-id
Interaction Testing
agent-browser click [data-testid='button']
agent-browser wait 500
agent-browser is visible [data-testid='result']
Form Testing
agent-browser fill [data-testid='input'] "test value"
agent-browser click [data-testid='submit']
agent-browser wait 1000
agent-browser is visible [data-testid='success']
Drag-Drop Testing
agent-browser snapshot -i -c
agent-browser drag @e5 @e8
agent-browser wait 500
agent-browser screenshot "$RALPHX_AGENT_SCREENSHOT_DIR/after-drag.png"
Text Verification
agent-browser get text [data-testid='title']
# Compare output with expected value
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.
- 1mo ago First seen · 182 lines · 14 tokens per session scan A 0c1c43047c1f
qa-step-generation is a skill published in the GitHub repository aigentive/RalphX (5 stars, last pushed 24d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,169 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…