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 agentmods add rules/kubev2v/forklift-console-plugin/taking-screenshotsgit clone --depth 1 https://github.com/kubev2v/forklift-console-pluginWrote 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/rules/kubev2v/forklift-console-plugin/taking-screenshots)<a href="https://agentmods.dev/rules/kubev2v/forklift-console-plugin/taking-screenshots"><img src="https://agentmods.dev/badge/rules/kubev2v/forklift-console-plugin/taking-screenshots.svg" alt="Measured on agentmods" 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 | $0.00011 | $0.03663 |
| Opus 5 | $0.00005 | $0.01832 |
| Sonnet 5 | $0.00002 | $0.00733 |
| Haiku 4.5 | $0.00001 | $0.00366 |
Grade A, and why
taking-screenshots scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w "%{http_code}" http://localhost:9000/ How it starts
The opening of the file, as written. The whole thing — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taking Screenshots & Screen Recordings
Rules for capturing UI screenshots (Playwright MCP) and screen recordings (video-recorder MCP) for PR demos.
1. Screenshot Location
Save all screenshots to the user's Downloads directory under a ticket-keyed folder:
~/Downloads/{TICKET_KEY}/
MTV-XXXX-1-description.png
MTV-XXXX-2-description.png
...
Create the directory if it doesn't exist. Never save screenshots to the project directory.
PR Image Upload
Use the gh attach CLI extension to upload images for PR descriptions:
# Upload and get the URL
gh attach upload ~/Downloads/{TICKET_KEY}/image.png \
--target kubev2v/forklift-console-plugin#<PR_NUMBER> \
--strategy release-asset \
--format url
This produces a GitHub-hosted URL that renders inline in markdown. Use the
returned URL in the PR body as .
Images are stored as release assets under the _gh-attach-assets tag on the
target repo. The release-asset strategy works with gh auth token -- no
browser session needed.
2. File Naming
Format: {TICKET_KEY}-{index}-{short-description}.png
- Use the ticket key (e.g.,
MTV-2482) - Append an incrementing index starting at 1
- Add a brief kebab-case description of what the screenshot shows
- Example:
MTV-2482-1-plan-details-header.png,MTV-2482-2-inspect-modal.png
3. Browser Setup
Before taking screenshots:
- Resize the browser:
browser_resize -> { width: 1920, height: 1080 } - Wait for the page to fully load before capturing
- If the target element is below the fold, scroll to it or use
fullPage: true - The 1920x1080 viewport matches a standard monitor; the sidebar uses ~250px leaving ~1670px for content. This is acceptable -- do NOT use larger viewports
4. Ticket-Driven Testing
Before taking any screenshots, re-read the Jira ticket. The screenshots must prove the fix works according to the ticket, not just show UI components exist.
Preparation
- Read the ticket's Steps to Reproduce, Actual Results, and Expected Results.
- Plan screenshots that demonstrate the transition from actual to expected.
- Follow the ticket's user flow, not the code change list.
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.
- 3d ago First seen · 420 lines · 11 tokens per session scan A 57046a4c364f
taking-screenshots is a cursor rule published in the GitHub repository kubev2v/forklift-console-plugin (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 11 tokens to every session and 3,663 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
e2e-authoring
E2E testing with Cypress and Cucumber, feature files, step definitions, page objects, fluent interface, assertions, data-app-busy / waitUntilAppIsNotBusy pairing, test execution.
webdriver-management
Selenium WebDriver lifecycle management — driver factory, explicit waits, browser options, and teardown.
vasu-playwright-utils
../../templates/cursor-rules/vasu-playwright-utils.mdc.
playwright-agents
../../templates/cursor-rules/playwright-agents.mdc.
qa-script-executor
QA Script Executor - Executes natural language test scripts using Chrome DevTools MCP and enhances them with technical hints.
cursorrule
A Model Context Protocol (MCP) server for automating Playwright tests.