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.
git clone --depth 1 https://github.com/daniel-bogale/anti-ai-writing-humanizerWrote 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/rules/daniel-bogale/anti-ai-writing-humanizer/anti-ai-writing-humanizer)<a href="https://agentmods.dev/rules/daniel-bogale/anti-ai-writing-humanizer/anti-ai-writing-humanizer"><img src="https://agentmods.dev/badge/rules/daniel-bogale/anti-ai-writing-humanizer/anti-ai-writing-humanizer/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/rules/daniel-bogale/anti-ai-writing-humanizer/anti-ai-writing-humanizer"><img src="https://agentmods.dev/badge/rules/daniel-bogale/anti-ai-writing-humanizer/anti-ai-writing-humanizer.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 | $0.00000 | $0.01494 |
| Opus 5 | $0.00000 | $0.00747 |
| Sonnet 5 | $0.00000 | $0.00299 |
| Haiku 4.5 | $0.00000 | $0.00149 |
Grade A, and why
anti-ai-writing-humanizer 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanize writing — remove AI tells
Write prose a human can deliver as their own, or rewrite existing prose so it stops reading as AI. Humanizing is mostly subtraction: cut the framing, keep the specific fact. Don't invent "human texture" — that's its own tell. Preserve meaning, facts, numbers, names, quotes, and citations exactly. Apply to prose only — never to code, code comments, or technical config.
The root cause of every tell below: LLMs regress to the mean, swapping specific facts for generic, positive-sounding phrasing. Push back toward the specific — name the date, number, person, or what actually happened, and cut the framing around it.
1. Use the plain word
Replace inflated vocab with the ordinary one (or cut it). Swapping one banned word for another ("leverage" → "harness") doesn't help.
| Don't write | Write |
|---|---|
| delve into | look at, dig into |
| showcase / highlight (verb) / underscore | show, point to |
| foster | build, support |
| garner | get, earn |
| leverage | use |
| enhance | improve |
| align with / resonate with | match, fit — or cut |
| serves as / stands as / serves as a testament to | is, shows, proves |
| features / offers / boasts | has |
| pivotal / crucial / vital / key (adj.) | important — or cut |
| tapestry / rich tapestry | cut |
| landscape / evolving landscape | name the field ("the industry") |
| realm / journey | area, field |
| vibrant / intricate | describe what's specifically lively/complex |
| valuable insights | state the insight |
| Additionally / Moreover / Furthermore (openers) | start the sentence, or "also" |
| It is worth noting that | delete |
| utilize / facilitate / numerous | use / help / many |
| in order to / due to the fact that / in the event that | to / because / if |
2. Direct, uneven sentences
- Use is/are/has — don't dress simple facts in elaborate verbs.
- No "not just X, but Y" / "not X, but Y" parallelism. Pick one, or use a plain "but".
- No rule-of-three padding ("keynotes, panels, and networking"). Be specific or say one thing well.
- Repeat the noun — don't cycle synonyms for the same thing.
- No false "from X to Y" ranges unless they're real endpoints on a real scale.
- End at the fact. Cut "-ing" tack-ons that add interpretation ("…creating a vibrant community").
- Vary sentence length. Metronomic pacing is the #1 detection signal; put a short sentence next to a long one.
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 · +20 lines d2d7519fedc1
- 12d ago First seen · 85 lines · 0 tokens per session scan A 44b8005f3d91
anti-ai-writing-humanizer is a cursor rule published in the GitHub repository daniel-bogale/anti-ai-writing-humanizer (4 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,494 tokens. 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.
Other cursor rules, from other repositories
humanizer
Humanize AI-sounding prose, rewrite in a writer's voice, and conservatively clean suspicious invisible Unicode in supplied prose. Use whenever the user wants to humanize, de-slop, de-AI, or de-robotify text; fix writing that sounds like an LLM, corporate, salesy, generic, or off; make a draft sound like them or a…
cursor-rules
Anti-AI-tell writing rules. Apply to all prose output (docs, comments, commit messages, README content, user-facing strings).
authenticity-check
Score how authentically text reads as a real human author's work, flag AI-generated, AI-templated, or derivative spans, and report suspicious Unicode provenance carriers. Use when the user asks if text is authentic, reads like AI, sounds like them, or contains a hidden AI watermark or invisible Unicode. Apply even…
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.