avoid-ai-writing is a portable writing skill that detects common patterns associated with AI-generated prose and can rewrite them or make targeted edits to prose files. It is for users of Claude Code, OpenClaw, Hermes, and other compatible coding agents who want text to sound more like human writing. The catalogue entries are the skill's rule and instruction components.
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 conorbronsdon/avoid-ai-writing --skill avoid-ai-writinggit clone --depth 1 https://github.com/conorbronsdon/avoid-ai-writingWrote 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/conorbronsdon/avoid-ai-writing/avoid-ai-writing)<a href="https://agentmods.dev/skills/conorbronsdon/avoid-ai-writing/avoid-ai-writing"><img src="https://agentmods.dev/badge/skills/conorbronsdon/avoid-ai-writing/avoid-ai-writing.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 5.1 | $0.00097 | $0.04716 |
| Opus 5 | $0.00048 | $0.02358 |
| Sonnet 5 | $0.00019 | $0.00943 |
| Haiku 4.5 | $0.00010 | $0.00472 |
Grade A, and why
avoid-ai-writing 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 today.
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.
Copies of this mod
3 near-identical copies found in the catalogue:
- avoid-ai-writing — 91% identical, 734 lines differ
- avoid-ai-writing — 91% identical, 614 lines differ
- avoid-ai-writing — 86% identical, 616 lines differ
How it starts
The opening of the file, as written. The whole thing — 225 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.
Before auditing or rewriting any text, read references/patterns.md in full. It contains the word tiers, pattern catalog, and context/voice profiles. These rules and their exceptions are required for quick passes as well as full audits. Resolve bundled command and example paths from this skill directory.
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
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.
- today Changed df5cc3733e14
- yesterday Changed · -648 lines c85a62d36980
- 2d ago Changed · +24 lines 38f40a579ad2
- 8d ago First seen · 849 lines · 97 tokens per session scan A 28272be8448f
avoid-ai-writing is a skill published in the GitHub repository conorbronsdon/avoid-ai-writing (4,163 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 4,716 once invoked, about $0.0005 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
unmachined
Finds and removes AI slop from prose, UX copy, and web interfaces. Use when writing, auditing, or revising articles, posts, READMEs, marketing copy, UI copy, layouts, or frontend code that must not feel AI-generated; when the user says unmachined, de-slop, AI slop, anti-slop, humanize, make this human, sounds like AI…
compress
Prompt-Studio memory compressor. Shrinks CLAUDE.md, todo lists, and preference files into Prompt-Studio's lean format to cut input tokens on every load. Preserves all technical substance, code, URLs, and structure. Compressed output overwrites the original; human-readable backup stored out-of-tree as FILE.original.md…
lean-commit
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes…
lean-gain
Show Lean's measured impact as a compact scoreboard: less code, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /lean-gain, "lean gain", "what does lean save", "show lean impact", "lean scoreboard".
lean-debt
Harvest every lean: comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals Lean leaves behind get tracked instead of rotting into "later means never". Use when the user says "lean debt", "/lean-debt", "what did lean defer", "list the shortcuts", "lean ledger", or "what did we mark to do…
lean-help
Quick-reference card for all Lean modes, skills, and commands. One-shot display, not a persistent mode: shows the card and exits without switching levels, writing flag files, or persisting anything. Trigger: /lean-help, "lean help", "what lean commands", "how do I use lean", "lean cheatsheet", "lean reference".