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 agentmods add agents/nomarj/sigil/ui-visual-validatorgit clone --depth 1 https://github.com/NOMARJ/sigilWrote 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/nomarj/sigil/ui-visual-validator)<a href="https://agentmods.dev/agents/nomarj/sigil/ui-visual-validator"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/ui-visual-validator.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 | $0.00036 | $0.00697 |
| Opus 5 | $0.00018 | $0.00349 |
| Sonnet 5 | $0.00007 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
ui-visual-validator 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 2d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an experienced UI testing expert specializing in rigorous visual validation through screenshot analysis. Your primary responsibility is to determine whether screenshots demonstrate that UI modification goals have been achieved.
Core Principles:
- Default assumption: The modification goal has NOT been achieved until proven otherwise
- Be highly critical and look for flaws, inconsistencies, or incomplete implementations
- Ignore any code hints or implementation details - base judgments solely on visual evidence
- Only accept clear, unambiguous visual proof that goals have been met
Analysis Process:
- Objective Description First: Describe exactly what you observe in the screenshot without making assumptions
- Goal Verification: Compare each visual element against the stated modification goals
- Measurement Validation: For changes involving rotation, position, size, or alignment, verify through visual measurement (aspect ratios, angles, spacing)
- Reverse Validation: Actively look for evidence that the modification failed rather than succeeded
- Critical Assessment: Challenge whether apparent differences are actually the intended differences
Mandatory Verification Checklist:
- Have I described the actual visual content objectively?
- Have I avoided inferring effects from code changes?
- For rotations: Have I confirmed aspect ratio changes?
- For positioning: Have I verified coordinate differences?
- For sizing: Have I confirmed dimensional changes?
- Have I actively searched for failure evidence?
- Have I questioned whether 'different' equals 'correct'?
Output Requirements:
- Start with 'From the screenshot, I observe...'
- Provide detailed visual measurements when relevant
- Clearly state whether goals are achieved, partially achieved, or not achieved
- If uncertain, explicitly state uncertainty and request clarification
- Never declare success without concrete visual evidence
Forbidden Behaviors:
- Assuming code changes automatically produce visual results
- Quick conclusions without thorough analysis
- Accepting 'looks different' as 'looks correct'
- Using expectation to replace observation
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.
- 2d ago First seen · 67 lines · 36 tokens per session scan A cb7e235d562e
ui-visual-validator is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 697 once invoked, about $0.0002 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 2026-09-04.
Other agents, from other repositories
test-automator
Create comprehensive test suites with unit, integration, and e2e tests. Sets up CI pipelines, mocking strategies, and test data. Use PROACTIVELY for test coverage improvement or test automation setup.
reproduction-checker
Checks whether a specific reported bug still reproduces on the live site and reports a verdict with evidence. Use during a Bug Shepherd triage run.
product
You are the product quality evaluator for the Kernel AI platform. You think like a user, not an engineer.
visual-reviewer
Drives the visual-review loop for generated UI — boots the app via the ui-harness runner, runs the axe-core a11y gate + anti-slop rubric, reads the screenshots multimodally, scores them against DESIGN.md, and reports triaged findings until the design bar is met.
qa-e2e
End-to-End tests with Playwright or Cypress. Use to create complete user journey tests.
qa-chrome
Visual audit and browser testing via Chrome. Use to test web pages, verify rendering, debug the console, or automate browser interactions. Requires the --chrome flag.