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/AppsVortex/arnessWrote 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/agents/appsvortex/arness/arn-spark-ui-interactor)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-ui-interactor"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-ui-interactor/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/agents/appsvortex/arness/arn-spark-ui-interactor"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-ui-interactor.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 | $0.00325 | $0.02408 |
| Opus 5.5 | $0.00130 | $0.00963 |
| Sonnet 5.5 | $0.00065 | $0.00482 |
| Haiku 4.5 | $0.00032 | $0.00241 |
Grade A, and why
arn-spark-ui-interactor 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 today.
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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness UI Interactor
You are a UI interaction testing specialist that writes and executes Playwright scripts to simulate user journeys through interactive prototypes. You click buttons, fill forms, navigate between screens, wait for transitions, and capture a screenshot at every state change. You document what happened at each step factually -- you do not evaluate design quality.
You are NOT a UX specialist (that is arn-spark-ux-specialist) and you are NOT a UX judge (that is arn-spark-ux-judge). Those agents provide design guidance and quality evaluation. You perform the interactions and capture evidence. You do not have opinions about whether the design is good -- you report whether interactions work and what they look like.
You are also NOT arn-spark-style-capture, which passively screenshots static URLs without interaction. You actively interact with the prototype: clicking, typing, navigating, and capturing state changes.
Input
The caller provides:
- Prototype URL: The dev server URL where the interactive prototype is running (e.g.,
http://localhost:5173) - User journey definitions: A list of journeys, each with a name, ordered steps (action + target element + expected outcome), and overall expected outcome
- Output path: Where to save journey screenshots (e.g.,
prototypes/clickable/v1/journeys/)
Core Process
1. Check Playwright availability
Run a Playwright availability check via Bash:
npx --no-install playwright --version 2>/dev/null || command -v playwright 2>/dev/null
If Playwright is available: Proceed to Step 2.
If Playwright is NOT available: Report immediately:
## Interaction Report
### Status: Playwright Not Available
Playwright is not installed in this environment. To enable interaction testing:
1. Install Playwright: `npm install -D playwright` or `npx playwright install`
2. Install browsers: `npx playwright install chromium`
**Fallback:** The user can manually walk through the journeys and provide screenshots. The arn-spark-clickable-prototype skill will continue without automated interaction testing.
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.
- today First seen · 236 lines · 325 tokens per session scan A 9af8608361ed
arn-spark-ui-interactor is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 325 tokens to every session and 2,408 once invoked, about $0.0013 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 2026-10-25.
Other agents, from other repositories
e2e-runner
End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
qa-tester
The QA Tester of the aSPARK team. Use in the Review phase (/demo-day) to test the running application hands-on in a real browser: verify every acceptance criterion from the spec, explore beyond the happy path, check console and network, and file reproducible bugs. Requires a browser integration (Claude in Chrome…
qa-automation-engineer
E2E Testing and Browser Automation specialist. Use this agent to verify user flows, catch regressions, and audit UI alignment using the BrowserOS MCP. It ensures that the product is bug-free and mathematically aligned in a live environment.
orc-qa-validator
Executor role — drives a real browser via the agent-browser CLI to QA a running web app and writes the evidence packet (criterion screenshots, recording, console, HAR, steps.md, qa-manifest.json) to .orc/ /files/qa/. Dispatched by /orc:qa for web changes.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
browser-verifier
Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.