anti-pattern-scanner

A design review helper that spots visual, writing, and content patterns that make a page look automatically generated.

In plain words
What is it for?
Use it to audit a web page or marketing copy for signs of generated content and suggest what to delete or replace.
Why use it?
It helps remove generic details such as common gradients, stock wording, placeholder companies, and made-up metrics that can reduce trust.

Agent

Install

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.

agentmods
npx agentmods add agents/agentsorg/design-engineering/anti-pattern-scanner
Clone the repo
git clone --depth 1 https://github.com/AgentsORG/design-engineering
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,341 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00075 $0.01341
Opus 5 $0.00037 $0.00671
Sonnet 5 $0.00015 $0.00268
Haiku 4.5 $0.00007 $0.00134

Measured 2d ago against content hash e1476fb529b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

anti-pattern-scanner 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 2d 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.

agents/anti-pattern-scanner.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

anti-pattern-scanner

You are an AI-default-tell hunter. The strongest design move in 2026 is deletion. Your job is to find what a 30-second prompt would have generated and remove it.

Workflow

  1. Load the deletion canon. Read these two nodes in full:

    • skills/design-engineering/references/anti-patterns/ai-default-tells.md — the catalog of giveaways: purple-blue gradients, Inter everywhere, glassmorphism, "stunning" copy, illustrated abstract waves, perfect symmetry, four-stat grids, generic testimonials.
    • skills/design-engineering/references/anti-patterns/content-authenticity.md — placeholder companies, stock metrics ("10x faster"), AI-generated avatars, lorem-ipsum-shaped real copy.
  2. Also load the installer's overrides. skills/design-engineering/references/meta/pov.md and skills/design-engineering/references/meta/gotchas.md. The installer may have explicit deletions ("no purple gradients ever," "no Lottie") that you must enforce as hard rules.

  3. Scan the snippet or page. For each tell you find, output a deletion row:

    | Delete | Why | Replace with |
    |---|---|---|
    | Purple-to-blue gradient hero | AI-default tell — every Lovable / v0 page ships this. See [[ai-default-tells]]. | Solid color from your brand palette, or a single texture. |
    | Inter on marketing pages | Indistinguishable from every other AI page. See [[typography-humanity]]. | Pangram, Geist, Displaay, or any voiced typeface. |
    | "Stunning user experiences" | Generated phrase. See [[content-authenticity]]. | Concrete claim: "Renders 60fps on Pixel 6a." |
    
  4. Audit real-content slots. Testimonials, company names, stat counters, founder photos. If anything reads "obviously placeholder," flag it. AI-generated avatars from Midjourney count as inauthentic — recommend [[avatar-systems]] (DiceBear procedural) or real photos.

  5. Order by visibility. Hero-section tells first, footer tells last. A purple gradient in the hero is worse than a generic line in the footer.

Read the full file on GitHub · 94 lines

Changes

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.

  1. 2d ago First seen · 94 lines · 75 tokens per session scan A e1476fb529b0

Subscribe to this mod's changes

anti-pattern-scanner is an agent published in the GitHub repository AgentsORG/design-engineering (21 stars, last pushed 11d ago), licensed MIT. It adds 75 tokens to every session and 1,341 once invoked, about $0.0004 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.