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 Akakaui/visual-browser-agent --skill evidence-reviewgit clone --depth 1 https://github.com/Akakaui/visual-browser-agentWrote 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/akakaui/visual-browser-agent/evidence-review)<a href="https://agentmods.dev/skills/akakaui/visual-browser-agent/evidence-review"><img src="https://agentmods.dev/badge/skills/akakaui/visual-browser-agent/evidence-review/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/akakaui/visual-browser-agent/evidence-review"><img src="https://agentmods.dev/badge/skills/akakaui/visual-browser-agent/evidence-review.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 | $0.00030 | $0.00991 |
| Opus 5 | $0.00015 | $0.00495 |
| Sonnet 5 | $0.00006 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
evidence-review 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 9d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Review Skill
When to Use
Use this skill to analyze visual evidence against requirements:
- Verify UI matches design specs
- Check accessibility compliance
- Validate responsive behavior
- Confirm animation quality
- Assess visual regression
- Make go/no-go decisions
Instructions
Review Process
For each evidence review request:
- Receive:
artifactPaths[],requirement,context - Call
review_visual_evidencewith all three - Get structured response:
passed,confidence,findings[] - Create evidence manifest with
nextDecision
Vision Analysis Capabilities
The reviewer can assess:
- Layout: Alignment, spacing, grid adherence
- Typography: Font family, size, weight, line height, color
- Color: Palette match, contrast ratios, semantic usage
- Components: Presence, state, variants
- Interactions: Hover/focus/active states visible
- Responsive: Breakpoint behavior, content reflow
- Motion: Animation smoothness, duration, easing
- Accessibility: Focus indicators, contrast, labels
- Content: Text accuracy, image presence, truncation
Confidence Scoring
- 0.9-1.0: Clear pass/fail, unambiguous
- 0.7-0.89: Likely correct, minor uncertainty
- 0.5-0.69: Ambiguous, needs human review
- <0.5: Cannot determine, escalate
Decision Mapping
| Confidence | Passed | Next Decision |
|---|---|---|
| ≥0.9 | true | continue |
| ≥0.9 | false | retry / human |
| 0.7-0.89 | true | continue |
| 0.7-0.89 | false | retry / human |
| <0.7 | any | human |
Findings Format
{
"type": "layout" | "typography" | "color" | "interaction" | "accessibility" | "content" | "performance",
"severity": "critical" | "major" | "minor" | "info",
"element": "selector or description",
"expected": "what should be",
"actual": "what is",
"wcag": "optional WCAG reference"
}
Output: Evidence Manifest
{
"eventId": "event-042",
"action": "review_checkout_button",
"requirement": "Primary CTA meets WCAG AA contrast and 44px touch target",
"artifacts": ["frames/checkout-cta.png"],
"review": {
"passed": false,
"confidence": 0.92,
"findings": [
{
"type": "accessibility",
"severity": "major",
"element": ".btn-primary",
"expected": "4.5:1 contrast ratio",
"actual": "3.2:1 contrast ratio",
"wcag": "1.4.3 Contrast (Minimum)"
},
{
"type": "interaction",
"severity": "minor",
"element": ".btn-primary",
"expected": "≥44px touch target",
"actual": "40px height"
}
]
},
"nextDecision": "human"
}
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.
- 9d ago First seen · 128 lines · 30 tokens per session scan A 26d2a05033c1
evidence-review is a skill published in the GitHub repository Akakaui/visual-browser-agent (0 stars, last pushed 15d ago), licensed MIT. It adds 30 tokens to every session and 991 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.