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.
git clone --depth 1 https://github.com/azam-sdet/10xqualityWrote 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/azam-sdet/10xquality/001-ui-automation-conventions)<a href="https://agentmods.dev/rules/azam-sdet/10xquality/001-ui-automation-conventions"><img src="https://agentmods.dev/badge/rules/azam-sdet/10xquality/001-ui-automation-conventions/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/rules/azam-sdet/10xquality/001-ui-automation-conventions"><img src="https://agentmods.dev/badge/rules/azam-sdet/10xquality/001-ui-automation-conventions.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 | $0.01129 | $0.01129 |
| Opus 5 | $0.00564 | $0.00564 |
| Sonnet 5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
001-ui-automation-conventions 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 12d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome DevTools MCP UI Automation Conventions
Use the chrome-devtools MCP server for all browser automation. Follow these conventions for reliable, repeatable test execution.
Snapshot-First Rule (CRITICAL)
ALWAYS take a snapshot before interacting with any element.
- Use
take_snapshotviachrome-devtoolsto understand the current page state - Use the uid from the latest snapshot — snapshots become stale after page changes
- NEVER guess uids — always get them from a fresh snapshot
- After navigation or clicks that trigger page changes, take a new snapshot
- Prefer taking a snapshot over taking a screenshot for element identification
Correct flow:
1. take_snapshot
2. Parse snapshot for uid of target element
3. click { uid: "..." }
4. take_snapshot (page changed)
5. Parse next element...
MCP Tool Reference (chrome-devtools)
| Action | Tool | Key Parameters |
|---|---|---|
| Navigate to URL | navigate_page |
type: "url", url: "..." |
| Go back | navigate_page |
type: "back" |
| Go forward | navigate_page |
type: "forward" |
| Reload | navigate_page |
type: "reload" |
| Take page snapshot | take_snapshot |
verbose: true (optional), filePath: "..." (optional) |
| Click element | click |
uid: "..." (required), dblClick: true (optional) |
| Fill input | fill |
uid: "...", value: "..." |
| Press key | press_key |
key name |
| Hover element | hover |
uid: "..." |
| Take screenshot | take_screenshot |
filePath: "..." (optional) |
| Wait for text | wait_for |
text: ["..."], timeout: N (optional) |
| Set viewport | emulate |
viewport: "<width>x<height>x<dpr>[,mobile][,touch][,landscape]" |
| List open pages | list_pages |
- |
| Select a page | select_page |
page identifier |
| Handle dialog | handle_dialog |
`action: "accept" |
| Drag element | drag |
source and target uids |
| Fill form | fill_form |
multiple fields |
| Evaluate script | evaluate_script |
function: "() => { ... }", args: [...] (optional) |
| New page | new_page |
url: "..." (optional) |
| Close page | close_page |
- |
| Resize page | resize_page |
dimensions |
| Upload file | upload_file |
uid: "...", file path |
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.
- 12d ago First seen · 112 lines · 1,129 tokens per session scan A ce509e20d9aa
001-ui-automation-conventions is a cursor rule published in the GitHub repository azam-sdet/10xquality (2 stars, last pushed 6mo ago), licensed MIT. It adds 1,129 tokens to every session, about $0.0056 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.
Other cursor rules, from other repositories
webkit-browser
Cursor rule "webkit-browser" from duckduckgo/apple-browsers, covering webkit & browser development guidelines, webview configuration, basic webview setup, user scripts management and tab management.
dev-browser
Fallback browser automation with persistent Chrome state. Use only when Browser Use is unavailable or blocked.
vasu-playwright-utils
../../templates/cursor-rules/vasu-playwright-utils.mdc.
chrome-extension-manifest-rules
Specific rules related to the Chrome extension manifest file, ensuring proper structure and content.
vla-registry
Multi-model GUI/VL registry — browser wllama grounding (ShowUI-2B is default + E2E gate).
safari
This file, safari.mdc, serves as a repository for detailed working notes, observations, and learnings acquired during the process of automating Safari interactions, particularly for the MCP Inspector UI. It's intended to capture the nuances of trial-and-error, debugging steps, and insights into what worked, what…