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 yarlson/yarstack --skill ui-controlgit clone --depth 1 https://github.com/yarlson/yarstackWrote 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/yarlson/yarstack/ui-control)<a href="https://agentmods.dev/skills/yarlson/yarstack/ui-control"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/ui-control/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/yarlson/yarstack/ui-control"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/ui-control.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 | $0.00049 | $0.00461 |
| Opus 5.5 | $0.00020 | $0.00184 |
| Sonnet 5.5 | $0.00010 | $0.00092 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
ui-control 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 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.
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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Control
Gather reproducible evidence from the actual graphical surface without changing production behavior.
Workflow
- Identify the target surface, build or session, and observable contract.
- Reuse the authorized running or authenticated surface when it is the target. Start a local app only when necessary and authorized. In a real authenticated session, an action can be an external write. Perform the interactions the user asked you to verify through the interface, such as submitting a form with invalid input to see it rejected. Never send requests directly to the server, and do not submit valid data, send, purchase, delete, or change settings beyond those interactions without explicit authority.
- Prefer existing repository harnesses. Otherwise use the host's browser tools, or Playwright when it is already installed; do not install automation for a one-off probe. Locate controls by stable roles, labels, identifiers, or application markers.
- Perform only actions needed for the requested behavior or a concrete risk. After each action, wait for its observable result instead of a fixed delay, and confirm it before the next action.
- Capture the smallest relevant screenshot, accessibility output, console entry, network evidence, or trace from the running interface. Markup or source code alone does not show behavior: observe it.
- Check loading, empty, error, keyboard, focus, responsive, and cleanup states only when material to the contract.
- Clean up only servers, profiles, sessions, and artifacts created by this workflow.
Keep verification read-only unless the parent task separately authorizes implementation. Use behavior-implement for fixes, phase-validate for contract acceptance, and test-gap-review for evidence sufficiency.
Do not retain sensitive evidence, use stale selectors, or terminate user-owned resources.
Finish with the surface tested, actions, observed result, retained evidence, and blockers or limitations. Label a general rule you infer from the observations, such as how a filter matches, as an inference, and name the inputs you tried.
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 Changed · +7 tokens per session e01717bbeec4
- 1mo ago First seen · 25 lines · 42 tokens per session scan A ca9e891eb6d1
ui-control is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 461 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 2026-08-31.
Other skills, from other repositories
write-e2e
Generate Playwright E2E tests from codebase analysis. Discovers routes, scores user flows by criticality, writes .spec.ts files that assert causality, and reports what was actually proven: GENERATED, STATICCHECKED, VERIFIEDLOCAL or VALIDATEDLIVE. Modes: --scope , --flow , --output , --base-url , --max-flows N, --live…
playwright
Use Playwright for browser testing, responsive verification, screenshots, console and network checks, forms, navigation, and important user flows.
test-conversion-reviewer
Reviewer for converting unit tests to browser tests for Project Bedrock. Invoke this when the user needs to review their work while removing complex Browser dependencies from tests.
playwright-skill
Complete browser automation with Playwright. Auto-detects dev servers, writes reusable test scripts, and supports screenshots, responsive checks, UX validation, login flows, link checks, and arbitrary browser automation. Use when the user wants to test a website, automate browser interactions, validate web…
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.
memstack-development-webapp-testing
Use when the user says 'write browser tests', 'test this page', 'playwright test', 'e2e test', 'end to end test', 'browser test', 'test the UI', or needs Playwright-based browser testing for a web application. Do NOT use for unit tests, API tests, or non-browser testing.