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 agentmods add skills/plugin87/full-stack-design-skills/anti-ai-design-patternsnpx skills add plugin87/full-stack-design-skills --skill anti-ai-design-patternsgit clone --depth 1 https://github.com/plugin87/full-stack-design-skillsWrote 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/plugin87/full-stack-design-skills/anti-ai-design-patterns)<a href="https://agentmods.dev/skills/plugin87/full-stack-design-skills/anti-ai-design-patterns"><img src="https://agentmods.dev/badge/skills/plugin87/full-stack-design-skills/anti-ai-design-patterns.svg" alt="Measured on agentmods" 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 | $0.00186 | $0.02457 |
| Opus 5 | $0.00093 | $0.01229 |
| Sonnet 5 | $0.00037 | $0.00491 |
| Haiku 4.5 | $0.00019 | $0.00246 |
Grade A, and why
anti-ai-design-patterns 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 5d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anti-AI Design Patterns
A field guide to the visual tells that mark an interface as machine-generated, and the intentional choices that replace them. The goal is not a different template — it is design that reads as deliberate: chosen neutrals, a real type system, asymmetry with reason, and iconography that belongs to one family.
Core principle: intentional beats default
An AI tell is almost never a single ugly element. It is the absence of a decision — the palette that was inherited instead of chosen, the border that decorates instead of encodes, the emoji dropped in because a real icon was more work. Every rule below reduces to one question:
Did a human decide this, or did it fall out of a default?
If you cannot state why a color, radius, border, or glyph is there, it is probably a tell.
1. The border tell — single-side accent rails
The single most common AI slop signature: a rounded card with a colored stripe on one side (usually left) and neutral borders on the other three.
/* ❌ AI TELL — accent rail on a rounded card */
.card {
border: 1px solid #e5e7eb;
border-left: 4px solid #6366f1; /* the giveaway */
border-radius: 12px;
}
Why it reads as AI: the accent has no informational job — it is applied to every card regardless of state, so it decorates rather than encodes. A colored edge on a rounded corner also fights the geometry (the stripe clips awkwardly at the radius).
Fixes — pick based on intent:
/* ✅ A. If the color means nothing: drop it. Let type + spacing carry the card. */
.card { border: 1px solid var(--line); border-radius: 12px; }
/* ✅ B. If the color must encode STATE (error/warn/success): use a full token
set — background tint + text + a same-color full border, not a lone rail. */
.card--critical {
border: 1px solid var(--danger-line);
background: var(--danger-bg);
color: var(--danger-ink);
}
/* ✅ C. If you genuinely want an edge accent, make it a deliberate full-bleed
top border on a SQUARE-topped card, or an inset marker — a decision, not a default. */
.stat { border-top: 3px solid var(--accent); border-radius: 0 0 10px 10px; }
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.
- 5d ago First seen · 190 lines · 0 tokens per session scan A f4bc43d9eea5
anti-ai-design-patterns is a skill published in the GitHub repository plugin87/full-stack-design-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 186 tokens to every session and 2,457 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…