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 tan-yong-sheng/ai-vision-mcp --skill visual-consistency-validationgit clone --depth 1 https://github.com/tan-yong-sheng/ai-vision-mcpWrote 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/tan-yong-sheng/ai-vision-mcp/visual-consistency-validation)<a href="https://agentmods.dev/skills/tan-yong-sheng/ai-vision-mcp/visual-consistency-validation"><img src="https://agentmods.dev/badge/skills/tan-yong-sheng/ai-vision-mcp/visual-consistency-validation/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/tan-yong-sheng/ai-vision-mcp/visual-consistency-validation"><img src="https://agentmods.dev/badge/skills/tan-yong-sheng/ai-vision-mcp/visual-consistency-validation.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 | $0.00028 | $0.00765 |
| Opus 5 | $0.00014 | $0.00382 |
| Sonnet 5 | $0.00006 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
visual-consistency-validation 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 11d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Consistency Validation Skill
Systematic approach to validating design system compliance across all breakpoints, modes, and interactive states.
Core Principle
Every violation must be: (1) mapped to a specific token, (2) quantified, (3) severity-categorized, and (4) provided with remediation. No rationalization allowed.
When to Use
- Validating component compliance against design system tokens
- Detecting visual regressions between baseline and updated designs
- Analyzing responsive design consistency (mobile, tablet, desktop)
- Validating dark mode and alternative state compliance
The Three Disciplines
1. Systematic Token Mapping
Every violation follows this template:
Property: [CSS property]
Current: [actual value]
Token: [token name from design system]
Expected: [token value]
Difference: [quantified: pixels, %, hex delta]
2. Comprehensive Coverage
Validate everything:
- All color properties (text, background, border, shadow, icon)
- All spacing (padding, margin, gap, position)
- All typography (size, weight, line-height, letter-spacing)
- All shapes (radius, borders, shadows)
- All animations (duration, easing)
- All breakpoints (mobile, tablet, desktop)
- All modes (light, dark, high-contrast)
- All interactive states (default, hover, focus, active, disabled)
3. Severity Categorization
| Level | When |
|---|---|
| CRITICAL | Accessibility/layout failures (WCAG contrast, broken states, layout shifts) |
| HIGH | Token violations with user impact (colors, spacing, typography) |
| MEDIUM | Minor deviations (< 10% difference) |
| LOW | Very minor (< 5% difference) |
Rule: All WCAG failures → CRITICAL (regardless of context).
Red Flags - STOP and Reanalyze
| Red Flag | What to Do |
|---|---|
| "Close enough" | Measure it. Report every difference. |
| "Desktop is primary" | Analyze all breakpoints equally. |
| "Light mode is primary" | Analyze all modes equally. |
| "Minor refinement" | Categorize by severity and report. |
| "Typical for design systems" | Escalate accessibility failures to CRITICAL. |
| "Not evaluating hover states" | Validate all interactive states. |
| "Acceptable variance" | Quantify and report every deviation. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 96 lines · 28 tokens per session scan A 55318fa951c1
visual-consistency-validation is a skill published in the GitHub repository tan-yong-sheng/ai-vision-mcp (78 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 765 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
design-qa
Internal prototype QA helper. Use only after a Product Design prototype, URL-to-code build, or image-to-code build has a source visual target and a rendered implementation to compare before handoff. Do not use for broad UX critique, design critique, product audits, or flow reviews; route those user-facing requests to…
health
Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application…
hunt
Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code…
chrome-cdp
Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…
ui-craft-checks
Use this comprehensive gate for formal review, QA, launch handoff, exact-fidelity inspection, high-risk complex UI, or when the fast gate exposes a deeper craft problem. Ordinary single-screen work uses ui-design-executor and its bundled validator without loading this full matrix. Pair standalone artifacts with…