Borrowing it
Nothing to install: this file belongs to saschb2b/okf-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saschb2b/okf-studio/main/.agents/skills/visual-consistency/SKILL.mdgit clone --depth 1 https://github.com/saschb2b/okf-studioWrote 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/saschb2b/okf-studio/visual-consistency)<a href="https://agentmods.dev/skills/saschb2b/okf-studio/visual-consistency"><img src="https://agentmods.dev/badge/skills/saschb2b/okf-studio/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/skills/saschb2b/okf-studio/visual-consistency"><img src="https://agentmods.dev/badge/skills/saschb2b/okf-studio/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 | $0.00219 | $0.02640 |
| Opus 5.5 | $0.00088 | $0.01056 |
| Sonnet 5.5 | $0.00044 | $0.00528 |
| Haiku 4.5 | $0.00022 | $0.00264 |
Grade A, and why
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 3d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Consistency
A detector and fixer for the visual and layout consistency defects that show up in rendered UI: the systematic raggedness an AI generator emits and a senior notices at a glance. It finds where repeated elements that should line up do not, where spacing is arbitrary instead of systematic, and where variable-length content breaks a clean layout, explains the cost of each, and proposes a concrete CSS fix with a source. The full catalog with detection signals, fixes, exceptions, severity, and sources is in catalog.md; copy-pasteable recipes for the flagship cases are in recipes.md. Read the catalog before a scan.
It defers two neighboring concerns to sibling skills so it does not duplicate them: color literals and contrast to theme-colors, and component, hook, and TypeScript code smells to react-stinky. The accessibility line splits the same way: this skill owns the visual and sizing side (target size, focus-ring consistency, reflow, text spacing the user can override), react-stinky owns the semantic-markup side (roles, labels, keyboard handlers). Whether a screen should exist at all is ask-ux, upstream of everything here. If a sibling is not installed, note the finding in one line and move on.
The four it was built for
These are the defects that prompted the skill. Each has a clean, modern fix; the rest of the catalog generalizes them.
- Uneven card heights in a grid. Cards in a row render at different heights because text length differs, so the grid looks busy. Grid and flex already stretch a row to its tallest card; the work is making the card a flex or grid column so its own footer pins to the bottom. See recipes.md.
- Sibling cards whose sections do not line up. Same template, but each card's title, body, and footer start at a different Y, so nothing scans across the row. The modern answer is CSS subgrid: declare the row tracks once on the grid and let each card inherit them, so the tallest title sets the title row for every card. See recipes.md.
- Trailing icons at ragged X positions. A list of links with an open-in-new-tab icon places the icon at a different X on every row because link text varies. Pin it with a two-column grid (
1fr auto), ormargin-inline-start: autoin a flex row, and addmin-width: 0so long text truncates instead of shoving the icon. See recipes.md. - Arbitrary, inconsistent spacing. Spacing falls back to off-scale magic numbers (
13px,7px,22px), or mixesmarginandgap, or pads similar containers differently. Snap every value to a spacing scale (4 and 8 point) referenced as a token, and prefer onegapon the parent over per-element margins. See recipes.md.
What ships with it
3 files 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.
- 3d ago First seen · 114 lines · 219 tokens per session scan A 2dfb37f9e0a1
visual-consistency is a skill published in the GitHub repository saschb2b/okf-studio (47 stars, last pushed yesterday), licensed MIT. It adds 219 tokens to every session and 2,640 once invoked, about $0.0009 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 2026-10-23.
Other skills, from other repositories
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
popular-web-designs
54 production-quality design systems extracted from real websites. Load a template to generate HTML/CSS that matches the visual identity of sites like Stripe, Linear, Vercel, Notion, Airbnb, and more. Each template includes colors, typography, components, layout rules, and ready-to-use CSS values.
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
hallmark
Use when designing, building, redesigning, or auditing websites and web pages that refuse to look AI-generated. Enforces anti-AI-slop design rules, non-waivable floor constraints, tokenized design systems, 48 curated themes/materials, and automated sloplint verification.