avoid-ai-writing

A set of editing rules for spotting and rewriting wording patterns often associated with AI-generated prose.

In plain words
What is it for?
Use it to audit or revise Markdown, documentation, blog posts, READMEs, release notes, and emails.
Why use it?
It helps make writing sound more natural while treating these patterns as signals rather than proof of who wrote the text.

Cursor rule

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 rules/natsummerance/readmd/avoid-ai-writing
Clone the repo
git clone --depth 1 https://github.com/Natsummerance/readMD
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 20,974 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin 94% copy Near-identical to another mod 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 $0.00000 $0.20974
Opus 5 $0.00000 $0.10487
Sonnet 5 $0.00000 $0.04195
Haiku 4.5 $0.00000 $0.02097

Measured 2d ago against content hash 49253218c73a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

avoid-ai-writing scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Curly quotation marks (“ ” ‘ ’) and apostrophes**: Curly quotes and apostrophes (U+201C/U+201D, U+2018/U+2019) are a *weak* paste-from-chat signal — meaningful mainly in plain-text contexts like code comments, commit
Origin

This is a copy

94% identical to avoid-ai-writing — 34 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

assets/upstream/conorbronsdon-avoid-ai-writing/40328bd292bc682d46010a6f9ac2cdbf4fb4ceca/cursor-rules/avoid-ai-writing.mdc · 806 lines

How it starts

The opening of the file, as written. The whole thing — 806 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Avoid AI Writing — Audit & Rewrite

You are editing content to remove AI writing patterns ("AI-isms") that make text sound machine-generated.

What this skill is and isn't

This is a writing-quality tool, not a verdict. The patterns flagged here are statistically more common in LLM output, but humans on autopilot — especially writing under deadline pressure, in unfamiliar genres, or in a second language — produce the same shapes. Independent audits of commercial AI detectors have found false-positive rates above 60% on non-native English writers (Liang et al., Stanford, Patterns 2023) and overall misclassification rates above 70% on open-source detectors (Jabarian & Imas, BFI Working Paper 2025-116, 2025). Adversarial paraphrase reduces detection accuracy by ~88% across every method tested (arXiv:2506.07001, 2025).

The patterns are useful as a signal — both for cleaning up your own writing and for assessing whether a piece reads as AI-generated. Just don't make them the sole basis for a consequential decision (academic integrity, hiring, publication, attribution). Several rules here also fire on second-language writing, deadline-pressed humans, and technical genres that compress vocabulary by design. Pair the signal with context: who wrote it, what genre, what the writer's normal voice looks like, what other evidence you have.

In short: signals, not proof. Worth acting on; not worth ruining someone's day over.

Modes

This skill operates in one of three modes:

rewrite (default) — Flag AI-isms and rewrite the text to fix them.

detect — Flag AI-isms only. No rewriting. Use this mode when:

  • The writer wants to see what's flagged and decide what to fix themselves
  • The flagged patterns might be intentional (AI patterns aren't always bad — they can be effective in small doses)
  • You're auditing text you don't want altered (published content, someone else's writing, reference material)
  • You want a quick scan without waiting for a full rewrite

Read the full file on GitHub · 806 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 · 806 lines · 0 tokens per session scan A 49253218c73a

Subscribe to this mod's changes

avoid-ai-writing is a cursor rule published in the GitHub repository Natsummerance/readMD (20 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 20,974 tokens. A static security scan graded it A with 1 finding (makes network calls). It is 94% identical to avoid-ai-writing, differing in 34 lines, and is treated as a copy.