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/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/commands/tan-yong-sheng/ai-vision-mcp/audit-visual-consistency)<a href="https://agentmods.dev/commands/tan-yong-sheng/ai-vision-mcp/audit-visual-consistency"><img src="https://agentmods.dev/badge/commands/tan-yong-sheng/ai-vision-mcp/audit-visual-consistency/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/commands/tan-yong-sheng/ai-vision-mcp/audit-visual-consistency"><img src="https://agentmods.dev/badge/commands/tan-yong-sheng/ai-vision-mcp/audit-visual-consistency.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 | $0.00023 | $0.00872 |
| Opus 5 | $0.00012 | $0.00436 |
| Sonnet 5 | $0.00005 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
audit-visual-consistency 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 12d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-eval:audit-visual-consistency
Validate design system token compliance on a single screenshot, or detect visual regressions by comparing baseline and current screenshots. Explicitly specify the analysis mode using --mode.
Arguments
| Argument | Description | Example |
|---|---|---|
--mode |
Analysis mode: token-compliance (single image) or regression (two images, baseline vs current). Default: token-compliance |
--mode token-compliance |
--imageSource |
URL, file path, or base64 image to validate (token-compliance mode only) | https://example.com/components.jpg |
--baseline |
Path/URL to baseline screenshot (regression mode only) | ./screenshots/baseline-mobile.jpg |
--current |
Path/URL to current screenshot (regression mode only, requires --baseline) |
./screenshots/current-mobile.jpg |
--design-system |
Path to DESIGN.md file for design-aware analysis (optional, both modes) | --design-system ./DESIGN.md |
--userPrompt |
Additional focus areas or custom instructions (optional) | --userPrompt "check button consistency" |
Mode 1: Token Compliance (Single Image)
Validate a single screenshot for design token compliance.
Mode: --mode token-compliance (default, can be omitted)
Syntax:
/design-eval:audit-visual-consistency --mode token-compliance --imageSource <source> [--design-system <path>]
Examples:
# Default token-compliance mode
/design-eval:audit-visual-consistency --imageSource https://example.com/components.jpg
# Explicit token-compliance with design system
/design-eval:audit-visual-consistency --mode token-compliance --imageSource ./ui-components.png --design-system ./DESIGN.md
# With custom focus
/design-eval:audit-visual-consistency --imageSource ./button.png --userPrompt "validate button color consistency"
Mode 2: Visual Regression (Two Images)
Detect visual regressions by comparing baseline and current screenshots.
Mode: --mode regression
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.
- 12d ago First seen · 88 lines · 23 tokens per session scan A 84acd59f50ad
audit-visual-consistency is a command published in the GitHub repository tan-yong-sheng/ai-vision-mcp (78 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 872 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 commands, from other repositories
qa
Verify the current work against the hard rules and the design.
p3-ux-a11y
Defines WCAG target, contrast requirements, keyboard navigation, screen reader requirements and testing methods.
kmp-audit-design-visual
Runs a visual-only audit of your app's Roborazzi screenshots using Claude vision. Detects design inconsistencies that have no code-level signal: spacing rhythm, color contrast, typography hierarchy, icon sizing, and alignment drift across screens.
playwright-test-heal
Run all my tests and fix the failing ones.
paul:verify
Guide manual user acceptance testing of recently built features.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.