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/tonyghiani/ai-essentialsWrote 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/tonyghiani/ai-essentials/no-ai-prose)<a href="https://agentmods.dev/rules/tonyghiani/ai-essentials/no-ai-prose"><img src="https://agentmods.dev/badge/rules/tonyghiani/ai-essentials/no-ai-prose.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 | $0.00863 | $0.00863 |
| Opus 5 | $0.00432 | $0.00432 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
no-ai-prose 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 7d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
No AI Prose
Default to natural, human-sounding writing in every output — chat responses, markdown files (.md, .mdx), code comments and docstrings, commit messages, PR descriptions, issue text, and anything else you write. Don't produce the patterns below.
Punctuation
- Do not use
-(space-hyphen-space) as a sentence-internal stop. Use commas, semicolons, or new sentences instead. - Same for
—(em-dash with spaces) when it would be the third or later dash in a paragraph. One per paragraph max. - Avoid stacking parentheticals:
foo (which is a thing) (used everywhere). Pick one and inline it.
Words and phrases — never use
These read as AI-flavoured, period:
leverage,utilize,delve,harness,unlock,streamlinerobust,comprehensive,seamless,powerful,cutting-edge,state-of-the-art,world-class(as generic adjectives)In conclusion,In summary,It's worth noting that,It goes without sayingMoreover,Furthermore,Additionally(use a fresh sentence or nothing)So,/Now,as sentence openers when they're verbal-tic fillerdive deep,take it to the next level,elevate your skillsIn this article we will explore,This article coversAs an AI,As a developer at(in author voice — be specific or omit)
Structural moves — don't do
- Restating what was just said. Move forward. If the previous paragraph said X, the next one does not begin "X means that...".
- Pre-announcing the section. Don't write "Let's now look at how to do Y" before a section titled "How to do Y". Just start the section.
- Concluding by restating every section heading. Land the plane in 1-3 short paragraphs. Trust the reader's memory.
- Padding around bullets. Don't write a paragraph that re-explains the bullets immediately above or below.
- Prerequisites / Table of Contents sections unless explicitly asked. Marco's posts never have these.
Adjective rule
If you reach for straightforward, robust, seamless, powerful, or simple — stop and replace with a specific reason it's good. Not "this approach is robust" but "this approach handles partial failures by retrying with backoff".
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.
- 7d ago First seen · 63 lines · 863 tokens per session scan A 15c08828d2b1
no-ai-prose is a cursor rule published in the GitHub repository tonyghiani/ai-essentials (6 stars, last pushed 1mo ago), licensed MIT. It adds 863 tokens to every session, about $0.0043 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
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.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.