anti-patterns

A set of guidelines for avoiding predictable mistakes in AI-produced code, designs, writing, and communication. It highlights problems such as unnecessary complexity, vague names, weak error handling, and stereotypical visual styles.

In plain words
What is it for?
Use it when reviewing or creating code, interface designs, written content, or messages, especially to remove over-engineering, generic naming, repeated comments, and common AI-style design choices.
Why use it?
It helps make generated work clearer, more maintainable, and less obviously machine-produced. It also encourages checking edge cases and explaining decisions instead of adding superficial comments.

Skill for Claude CodeCodex

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 skills/subhansh-dev/agent-maxxing/anti-patterns
Any agent
npx skills add subhansh-dev/agent-maxxing --skill anti-patterns
Clone the repo
git clone --depth 1 https://github.com/subhansh-dev/agent-maxxing

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 816 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 $0.00027 $0.00816
Opus 5 $0.00014 $0.00408
Sonnet 5 $0.00005 $0.00163
Haiku 4.5 $0.00003 $0.00082

Measured 2d ago against content hash 1093e664e0ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

anti-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 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.

engineering/anti-patterns/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anti-Patterns — What NOT To Do

Code Anti-Patterns

Over-Engineering

  • Building a framework when a function will do
  • Adding abstraction layers "for future flexibility" that never comes
  • Creating interfaces for things with only one implementation
  • Using design patterns where simple code works

Under-Thinking

  • Not reading the existing codebase before writing
  • Not handling errors ("it should work")
  • Not testing edge cases
  • Copy-pasting Stack Overflow without understanding it

Naming

  • data, temp, result, obj, item, thing — bad
  • handleClick, processData, manageState — too generic
  • Abbreviations nobody knows (cfg, mgr, util) — bad
  • Names that tell you what it IS, not what it DOES — good

Comments

  • Commenting every line — bad
  • Comments that restate the code (// increment i above i++) — bad
  • TODO comments that never get done — bad
  • Comments that explain WHY (decisions, trade-offs, workarounds) — good

Design Anti-Patterns

The AI Look

If your design has these, it looks AI-generated:

  • Purple-to-blue gradients
  • Glassmorphism everywhere
  • Neon accents on dark backgrounds
  • Inter/Roboto/Arial font
  • Identical card grids
  • Hero metric layout (big number, small label, gradient accent)
  • Gradient text on headings
  • Rounded rectangles with colored border on one side
  • Sparklines as decoration

The Safe Look

If your design has these, it looks boring:

  • Everything is the same size
  • Everything is centered
  • Gray on gray on gray
  • No personality, no focal point
  • Could be any company's website

The Chaos Look

If your design has these, it looks amateur:

  • Too many fonts (more than 2-3)
  • Too many colors (more than 4-5)
  • Too many animations
  • Everything is loud, nothing is quiet
  • No hierarchy, everything screams

Writing Anti-Patterns

AI Voice

These patterns scream "a robot wrote this":

  • "It's important to note that..."
  • "It's worth mentioning that..."
  • "In conclusion..."
  • "As we can see..."
  • "This serves as a testament to..."
  • "The vibrant tapestry of..."
  • Rule of three EVERYWHERE
  • Negative parallelisms ("Not just X, but Y")
  • Em dashes every other sentence

Read the full file on GitHub · 110 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 · 110 lines · 27 tokens per session scan A 1093e664e0ec

Subscribe to this mod's changes

anti-patterns is a skill published in the GitHub repository subhansh-dev/agent-maxxing (2 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 816 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 2026-08-31.