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 Zhang-Henry/CoEvoSkills --skill evo-nextjs-visual-stabilitygit clone --depth 1 https://github.com/Zhang-Henry/CoEvoSkillsWrote 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/zhang-henry/coevoskills/evo-nextjs-visual-stability)<a href="https://agentmods.dev/skills/zhang-henry/coevoskills/evo-nextjs-visual-stability"><img src="https://agentmods.dev/badge/skills/zhang-henry/coevoskills/evo-nextjs-visual-stability/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/zhang-henry/coevoskills/evo-nextjs-visual-stability"><img src="https://agentmods.dev/badge/skills/zhang-henry/coevoskills/evo-nextjs-visual-stability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.00436 |
| Opus 5 | $0.00023 | $0.00218 |
| Sonnet 5 | $0.00009 | $0.00087 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
evo-nextjs-visual-stability 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.
What it actually says
Next.js Visual Stability Fixer
This skill fixes common visual instability issues in Next.js apps:
- Theme flicker (FOUC): Adds blocking inline script to set theme before first paint
- Font FOIT: Adds
font-display: swapto@font-facerules - Image CLS: Adds width/height to images missing dimensions
- Async content CLS: Replaces
return nullloading states with space-reserving placeholders - Skeleton loaders: Uses skeleton components instead of text loading indicators
Usage
import sys
sys.path.insert(0, '/app/environment/skills/evo-nextjs-visual-stability/scripts')
from run_all_fixes import run_all_fixes, validate_fixes
# Apply all fixes
results = run_all_fixes('/app')
print(results)
# Validate
validation = validate_fixes('/app')
assert validation['valid'], f"Validation failed: {validation['issues']}"
Individual Fix Functions
import sys
sys.path.insert(0, '/app/environment/skills/evo-nextjs-visual-stability/scripts')
from fix_theme_flicker import fix_theme_flicker
from fix_font_display import fix_font_display
from fix_image_dimensions import fix_image_dimensions
from fix_async_placeholders import fix_banner_placeholder, fix_sidepane_placeholder, fix_resultsbar_placeholder
from fix_product_skeleton import fix_product_list_skeleton
Key Principles
- Never change existing class names, ids, or data-testid attributes
- Placeholders must use the same classes and testid as the final content
- Theme script must execute before first paint (in
<head>or early<body>) font-display: swapprevents FOIT- Images need both width and height for browser to reserve space
What ships with it
6 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.
- 12d ago First seen · 52 lines · 46 tokens per session scan A 32d641123d70
evo-nextjs-visual-stability is a skill published in the GitHub repository Zhang-Henry/CoEvoSkills (66 stars, last pushed 22d ago), licensed Apache-2.0. It adds 46 tokens to every session and 436 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 2026-08-30.
Other skills, from other repositories
shopify-theme-optimization
Theme speed and UX optimization — Core Web Vitals, Liquid code, image loading, mobile responsiveness.
shopify
Expert Shopify theme development guidelines for Liquid, Online Store 2.0, CSS, JavaScript, and UX best practices.
shopify-theme-development-guidelines
Expert Shopify theme development with Liquid, Online Store 2.0, and performance best practices.
sfcc-sfra-scss
Best practices for styling and theming SFRA storefronts using SCSS. Use when asked to create style overrides, theming, responsive layouts, or CSS customizations in SFCC.
wc-product-attribute-swatches
Build or audit WooCommerce product attribute swatch integrations around the experimental wc-visual attribute type. Covers feature gating, global pa attribute taxonomies, the WooCommerce 11 slug byte limit, color/image term meta, visual admin search results, Store API experimentalvisual / experimentalVisual, classic…
design-page
Turn an approved one-page storefront plan into canonical Lexsis source and an unpublished hosted draft, confirming any asset slots the plan left unresolved.