Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jpoutrin/product-forgenpx agentmods add skills/jpoutrin/product-forge/qa-element-extractionWrote 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/jpoutrin/product-forge/qa-element-extraction)<a href="https://agentmods.dev/skills/jpoutrin/product-forge/qa-element-extraction"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/qa-element-extraction/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/jpoutrin/product-forge/qa-element-extraction"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/qa-element-extraction.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 | $0.00040 | $0.01991 |
| Opus 5.5 | $0.00016 | $0.00796 |
| Sonnet 5.5 | $0.00008 | $0.00398 |
| Haiku 4.5 | $0.00004 | $0.00199 |
Grade A, and why
qa-element-extraction 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Element Extraction Skill
Capture targeted screenshots of UI elements referenced in test procedures to create visual documentation.
Purpose
When a test step says "Click the Login button", capture a screenshot of that specific button so testers know exactly what to look for. This creates a visual glossary alongside full-page screenshots.
Element Screenshot Directory
qa-tests/
├── active/
│ └── QA-20250105-001-login.md # QA test document
└── screenshots/
└── QA-20250105-001/ # Matches test-id
├── 01-initial-state.png # Full page screenshots
├── 02-form-filled.png
├── 03-success-state.png
└── elements/ # Extracted UI elements
├── login-button.png
├── email-field.png
└── password-field.png
Note: The {test-id} folder name (e.g., QA-20250105-001) matches the QA test document filename.
Element Extraction Process
Step 1: Parse Test Procedure
Identify actionable elements from test steps:
| Test Step Text | Element to Extract |
|---|---|
| "Click the Login button" | Login button |
| "Enter email in the Email field" | Email input field |
| "Select Settings from dropdown" | Settings menu item |
| "Check the Remember me checkbox" | Remember me checkbox |
| "Click the hamburger menu icon" | Hamburger menu icon |
Step 2: Element Identification Patterns
Look for these patterns in test steps:
Action + "the" + [Element Name] + element type
Action verbs to scan:
- Click, Tap, Press
- Enter, Type, Input
- Select, Choose, Pick
- Check, Uncheck, Toggle
- Hover, Focus
- Drag, Drop
- Scroll to
Element type keywords:
- button, btn, link
- field, input, textbox
- dropdown, select, combobox
- checkbox, radio, toggle
- icon, image, logo
- menu, nav, tab
- modal, dialog, popup
- card, tile, panel
Step 3: Capture Element
Using Playwright MCP:
// Find element by accessible name or text
const element = page.getByRole('button', { name: 'Login' });
// Capture just this element
await element.screenshot({
path: 'qa-tests/screenshots/QA-20250105-001/elements/login-button.png'
});
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 · 307 lines · 40 tokens per session scan A 6917e4b9dfd9
qa-element-extraction is a skill published in the GitHub repository jpoutrin/product-forge (16 stars, last pushed 7mo ago), licensed MIT. It adds 40 tokens to every session and 1,991 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
design-qa
Internal prototype QA helper. Use only after a Product Design prototype, URL-to-code build, or image-to-code build has a source visual target and a rendered implementation to compare before handoff. Do not use for broad UX critique, design critique, product audits, or flow reviews; route those user-facing requests to…
health
Audits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong. Not for application bugs or PR review.
hunt
Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or new features.
ui-craft-checks
Use this comprehensive gate for formal review, QA, launch handoff, exact-fidelity inspection, high-risk complex UI, or when the fast gate exposes a deeper craft problem. Ordinary single-screen work uses ui-design-executor and its bundled validator without loading this full matrix. Pair standalone artifacts with…
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.