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 conorluddy/xclaude-plugin --skill ui-automation-workflowsgit clone --depth 1 https://github.com/conorluddy/xclaude-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/skills/conorluddy/xclaude-plugin/ui-automation-workflows)<a href="https://agentmods.dev/skills/conorluddy/xclaude-plugin/ui-automation-workflows"><img src="https://agentmods.dev/badge/skills/conorluddy/xclaude-plugin/ui-automation-workflows.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 5.1 | $0.00072 | $0.02266 |
| Opus 5 | $0.00036 | $0.01133 |
| Sonnet 5 | $0.00014 | $0.00453 |
| Haiku 4.5 | $0.00007 | $0.00227 |
Grade A, and why
ui-automation-workflows 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 8d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Automation Workflows
Use the execute_idb_command MCP tool for all UI automation
The xclaude-plugin provides the execute_idb_command MCP tool which consolidates all IDB UI automation operations into a single, token-efficient dispatcher.
⚠️ CRITICAL: Always Use MCP Tools First
This is the most important rule: When automating UI interactions, you MUST use the execute_idb_command MCP tool.
- ✅ DO: Invoke
execute_idb_commandfor all UI automation, element finding, and accessibility queries - ✅ DO: If the MCP tool fails, adjust parameters and retry
- ✅ DO: Read error messages and debug the parameters
- ❌ NEVER: Fall back to bash
idbcommands - ❌ NEVER: Use
idbdirectly in bash - ❌ NEVER: Run
idbcommands in a terminal
Why? The MCP tool provides:
- Structured error handling
- Token efficiency (consolidated into 1 tool vs. verbose bash output)
- Proper integration with the xclaude-plugin architecture
- Accessibility-first patterns built-in
If execute_idb_command fails, the issue is with parameters or app state - not that you should use bash.
Core Principle: Accessibility Before Screenshots
Always query the accessibility tree first. Only use screenshots as a fallback.
Use the execute_idb_command MCP tool with operation describe to access the accessibility tree.
Why Accessibility-First?
| Approach | Time | Tokens | Reliability |
|---|---|---|---|
| Accessibility tree | ~120ms | ~50 | Survives theme changes |
| Screenshot | ~2000ms | ~170 | Breaks on visual changes |
Result: 3-4x faster, 80% cheaper, more reliable
Standard Workflow
1. Check Accessibility Quality (Optional) - Use execute_idb_command
Before starting automation, check if the app has good accessibility support:
Invoke the execute_idb_command MCP tool:
{
"operation": "check-accessibility",
"target": "booted"
}
Interprets:
- "excellent" or "good": Proceed with accessibility-first workflow
- "poor" or "insufficient": May need to rely more on screenshots
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.
- 8d ago First seen · 369 lines · 72 tokens per session scan A 6cb35ef465db
ui-automation-workflows is a skill published in the GitHub repository conorluddy/xclaude-plugin (182 stars, last pushed 7mo ago), licensed MIT. It adds 72 tokens to every session and 2,266 once invoked, about $0.0004 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.
Other skills, from other repositories
test-engineer
Automated E2E testing with Playwright including the auto-fix loop — generate test cases from the UI, run them, fix failures and re-run until passing, then produce a human-readable report. Test until it passes, not just test and report. Drives /toh-test; use whenever tests must be written, run, or made green.
runtime-verification
Verify code works at runtime through build verification (mandatory), LSP diagnostics, ad-hoc verification for projects without frameworks, E2E and smoke tests, and visual verification (screenshot-analyze-verify for UI changes). Skip whitelist strictly enforced (markdown-only, config-only, dependency-bump-only with…
visual-verification
Verify UI-facing changes by running a screenshot-analyze-verify loop across configured viewports, with a browser-tool priority cascade (Playwright MCP → Chrome DevTools MCP → CLI fallback → external skill fallback) and bounded iteration. Use after build/runtime verification passes and the diff includes…
parallel-lifecycle
Run and CDP-test a feature inside its own git worktree without colliding with other parallel coding sessions. Use whenever you are testing a feature locally in a worktree, running Playwright/CDP against your own app, or running two or more agent sessions in parallel that each need a dev server and a browser. Trigger…
e2e
Discover, operate, and incrementally extend a project's existing end-to-end test capability. Use when the user asks to run, check, inspect, or report E2E tests; validate a project or deployed environment end to end; identify E2E coverage gaps; or add and strengthen project-owned E2E cases. Follow project-owned tests…
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…