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.
Borrowing it
Nothing to install: this file belongs to conorbronsdon/avoid-ai-writing. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/conorbronsdon/avoid-ai-writing/main/CLAUDE.mdgit 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/instructions/conorbronsdon/avoid-ai-writing/claude-md)<a href="https://agentmods.dev/instructions/conorbronsdon/avoid-ai-writing/claude-md"><img src="https://agentmods.dev/badge/instructions/conorbronsdon/avoid-ai-writing/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/conorbronsdon/avoid-ai-writing/claude-md"><img src="https://agentmods.dev/badge/instructions/conorbronsdon/avoid-ai-writing/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01127 | $0.01127 |
| Opus 5.5 | $0.00451 | $0.00451 |
| Sonnet 5.5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
avoid-ai-writing CLAUDE.md 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 20d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
A directory-based writing skill (SKILL.md plus references/patterns.md) that audits and rewrites content to remove AI writing patterns. The skill is a markdown file consumed by AI coding assistants; the repository also includes a dependency-free deterministic detector and test suite.
Repository structure
SKILL.md— entry instructions, severity tiers, preservation rules, and output formats.references/patterns.md— canonical word tiers, catalog, context and voice profiles.SKILL.full.md— generated full source for comparison and self-scan.dist/avoid-ai-writing.md— generated portable paste instructions.README.md— public-facing docs, installation instructions, pattern reference table, full before/after example.CHANGELOG.md— version history with what changed and why.
How to make changes
Edit SKILL.md and references/patterns.md directly. When making changes:
- Follow the changelog and versioning policy: add an Unreleased entry for user-facing changes; routine docs corrections, tests, and maintenance with no user-facing effect need no entry or version bump.
- When preparing a release, update the SKILL.md frontmatter (
version: X.Y.Z),package.json, and the dated changelog heading. Update the same version manually in both plugin manifests before syncing:plugins/avoid-ai-writing/.claude-plugin/plugin.json.codex-plugin/plugin.json
- Update the same version in the six hand-written
skills/*/SKILL.mdfrontmatters (all but the generatedskills/avoid-ai-writing/SKILL.md).python3 scripts/validate-openai-plugin.py . --jsonfails when one differs from the OpenAI manifest. - Run
bash scripts/sync-plugin-skill.sh && bash scripts/sync-cursor-rules.sh. The first script validates both manifest versions and thepackage.jsonversion againstSKILL.mdand regenerates bundled skill copies, detector resources, scripts, and examples; the second regenerates the portable paste/Cursor artifacts. Neither script generates the manifest versions. A mismatch fails with messages such asversion mismatch: SKILL.md=X Claude plugin=Y,version mismatch: SKILL.md=X OpenAI plugin=Y, orversion mismatch: SKILL.md=X package.json=Y. - Run
npm testto exercise the detector, category contract, validator, corpus helpers, and style checks. - Update README.md if the change affects installation, usage, feature list, or pattern count
- The pattern count is canonical in the README "74 pattern categories" bullet (derived from references/patterns.md's detection
###entries). This bullet quotes that number here as a checked copy for agent context — update README and this sentence when you add or remove a detection category. Don't restate the count elsewhere; CI (scripts/check-pattern-count.sh) fails if either literal drifts fromreferences/patterns.md.
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.
- 20d ago Changed · +1 lines · +61 tokens per session 3c02886bc6d8
- 21d ago Changed · +20 tokens per session b73999a8b904
- 1mo ago Changed 3237bc8187a8
- 1mo ago Changed · -1 lines · +62 tokens per session b8052b8d9b2c
- 1mo ago Changed · +3 lines · +66 tokens per session d4e8bfba8206
- 1mo ago Changed · +4 lines · +106 tokens per session 8e409b93e7e3
- 1mo ago Changed 6af6bfa7fd4e
- 1mo ago First seen · 48 lines · 812 tokens per session scan A 8590c8b83d29
avoid-ai-writing CLAUDE.md is an instructions file published in the GitHub repository conorbronsdon/avoid-ai-writing (5,229 stars, last pushed 5d ago), licensed MIT. It adds 1,127 tokens to every session, about $0.0045 per session on Opus 5.5. 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.