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/MikkoParkkola/anti-ai-tellWrote 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/mikkoparkkola/anti-ai-tell/cursor-rules)<a href="https://agentmods.dev/rules/mikkoparkkola/anti-ai-tell/cursor-rules"><img src="https://agentmods.dev/badge/rules/mikkoparkkola/anti-ai-tell/cursor-rules/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/mikkoparkkola/anti-ai-tell/cursor-rules"><img src="https://agentmods.dev/badge/rules/mikkoparkkola/anti-ai-tell/cursor-rules.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 | $0.00410 | $0.00410 |
| Opus 5 | $0.00205 | $0.00205 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
cursor-rules 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 9d 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.
What it actually says
Writing style: no AI tells
When writing any prose (documentation, READMEs, comments, commit messages, PR descriptions, user-facing copy):
- Never use: delve, tapestry, showcase, underscore, meticulous, commendable, realm, elucidate, game-changer, ever-evolving (or their inflections).
- Ration (max one per document): intricate, pivotal, testament, vibrant, boast, garner, bolster, seamless, groundbreaking, cutting-edge, invaluable, leverage, harness, unveil, transformative, landscape.
- Write is/are/has, never "serves as / stands as / boasts / represents".
- No em-dashes. No "not X, but Y" constructions; assert directly.
- Mix sentence lengths; never three similar-length sentences in a row. Vary paragraph length.
- Concrete over abstract: numbers, names, dates, examples. Name sources; never "studies show" alone.
- Take positions with reasons. No symmetric hedging. Push back on wrong premises.
- No throat-clearing openers or "In conclusion" wrap-ups. No compulsive three-item lists.
- Before finishing prose, re-scan for em-dashes and banned words; fix them.
VISUAL/DESIGN: never ship AI design defaults (Tailwind indigo-500/purple gradients, Inter-only, untouched shadcn cards, 3-column icon grids, emoji headers, markdown bleed in docs, plastic skin / orange-teal / gradient-blob logos). Ask the user for a style anchor when none is set and keep it. Run: python3 visual_lint.py FILE.
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.
- 9d ago First seen · 25 lines · 410 tokens per session scan A 9be82ab2e593
cursor-rules is a cursor rule published in the GitHub repository MikkoParkkola/anti-ai-tell (3 stars, last pushed 5d ago), licensed MIT. It adds 410 tokens to every session, about $0.0020 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.
Other cursor rules, from other repositories
cursorrules
You are a senior TypeScript developer working on a Next.js 16 application.
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…
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…
anti-ai-writing-humanizer
Humanize prose — write or rewrite so it doesn't read as AI. Activate when editing prose-heavy files (Markdown, docs, blog posts, READMEs, release notes, emails) or when asked to "humanize", "remove AI-isms", or "make this sound human". Cursor port of the anti-ai-writing-humanizer skill. See…
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.