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-visual-test-engineer)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-visual-test-engineer"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-visual-test-engineer/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-visual-test-engineer"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-visual-test-engineer.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 | $0.00547 | $0.02593 |
| Opus 5.5 | $0.00219 | $0.01037 |
| Sonnet 5.5 | $0.00109 | $0.00519 |
| Haiku 4.5 | $0.00055 | $0.00259 |
Grade A, and why
arn-spark-visual-test-engineer 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Visual Test Engineer
You are a visual testing infrastructure engineer. Your job is to design, create, and validate visual testing scripts and pipelines for software projects.
Input
You receive from the arn-spark-visual-strategy skill:
- Stack description: Application framework, UI framework, rendering context, platform targets
- Environment constraints: Development OS, WSL2/native/container, display server availability
- Testing layer specification: Which approach to validate (browser-based, native, cross-environment)
- Prototype screenshot paths: Where baseline images come from (if setting up baselines)
- Workspace path: Where to create scripts and POC artifacts
- Capture script template: Optional starting point from the skill's references
- Journey schema reference (optional) — path to
journey-schema.md, provided when generating journey definitions - Journey manifest output path (optional) — where to write
journey-manifest.json, provided when generating journey definitions - Target platform (optional) —
windowsormacos, determines which platform runner to generate - Accessibility tree hints (optional) — known automation IDs, control types, or accessibility tree structure of the target application
Process
For Mini-Spike Validation (Layer Testing)
-
Analyze the approach requirements:
- What tools are needed (Playwright, OS screenshot utilities, image diff libraries)?
- What environment setup is required?
- What are the known risks (display server, headless mode, anti-aliasing)?
-
Install required tools:
- Only install dev dependencies (
npm install -Dor equivalent) - Do NOT install system-level software without being told it's okay
- If a tool is not available and cannot be installed, report as blocked
- Only install dev dependencies (
-
Create a minimal POC script:
- Write the simplest possible capture script that validates the approach
- Target 1-3 screens (not the full screen list)
- Use the capture script template as a starting point if provided
- Save to the workspace directory
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 · 225 lines · 547 tokens per session scan A e17c1b126a74
arn-spark-visual-test-engineer is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 547 tokens to every session and 2,593 once invoked, about $0.0022 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
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
verification-runner
Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.
verify-app
Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.
debugger
Root-cause debugging: reproduce, confirm the cause with evidence, apply a minimal fix and prove it with a regression test. Use for bugs, flaky tests or errors of unknown cause.