cursor

cursor is an agent for coding agents from Byk3y/no-slop. It costs 0 tokens per session (545 once invoked), scanned A, original, MIT.

A set of writing rules for Cursor, a coding editor with an AI assistant. The rules limit certain words and phrases in prose such as documentation, emails, comments, and pull-request descriptions.

In plain words
What is it for?
Use it by placing the rules in a project’s .cursorrules file so Cursor follows them when writing project prose.
Why use it?
It helps keep AI-written text closer to a plain, restrained style and avoids specified wording.

Agent

Install

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.

agentmods
npx agentmods add agents/byk3y/no-slop/cursor
Clone the repo
git clone --depth 1 https://github.com/Byk3y/no-slop

Wrote 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.

agentmods badge for cursor

README.md
[![agentmods](https://agentmods.dev/badge/agents/byk3y/no-slop/cursor.svg)](https://agentmods.dev/agents/byk3y/no-slop/cursor)
Your own site
<a href="https://agentmods.dev/agents/byk3y/no-slop/cursor"><img src="https://agentmods.dev/badge/agents/byk3y/no-slop/cursor.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 545 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00545
Opus 5 $0.00000 $0.00272
Sonnet 5 $0.00000 $0.00109
Haiku 4.5 $0.00000 $0.00055

Measured 4d ago against content hash f047486e90c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor 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 4d 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.

agents/cursor.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor

Install

Copy the rules below into your .cursorrules file at the root of your project. If you already have a .cursorrules file, append these rules to the end.

Rules

# no-slop — Anti-AI writing rules
# Source: https://github.com/Byk3y/no-slop

When writing prose (docs, emails, comments, READMEs, PR descriptions), follow these rules:

BANNED WORDS: Do not use: additionally, delve, tapestry, pivotal, vibrant, meticulous, landscape (metaphorical), testament, underscore, intricate, interplay, garner, bolster, foster, showcase, emphasize, enduring, crucial, enhance, highlighting, renowned, groundbreaking, profound, comprehensive, multifaceted, leverage, utilize, facilitate, encompasses, spearhead, harness, elevate, streamline, robust (in prose), seamless, holistic, synergy, paradigm, ecosystem (metaphorical).

BANNED PHRASES: Do not use: "marks a pivotal moment," "represents a significant shift," "indelible mark," "deeply rooted," "rich history," "nestled in," "boasts a," "serves as a," "stands as a," "not just X but Y," "despite its [positive], faces challenges," "let's explore," "in today's [landscape/world/era]," "at the heart of," "it is worth noting," "a testament to," "paving the way," "plays a crucial role," "in an era where," "the intersection of," "it remains to be seen."

COPULAS: Use "is," "are," "was," "has." Do not replace with "serves as," "stands as," "represents," "boasts," "features."

STRUCTURE: No rule-of-three patterns. No "not only X but also Y." No "challenges and future prospects" endings.

PARTICIPLES: Do not chain -ing words as filler: "highlighting," "showcasing," "emphasizing," "reflecting."

TONE: No promotional language. No vague attributions ("experts say"). No overstating significance. No collaborative language ("let's explore").

FORMATTING: Minimal bold. No emoji unless asked. Sentence-case headings. No "key takeaways" sections.

STYLE: Vary sentence length. Use contractions. Start sentences with "But," "And," "So" sometimes. Be specific — numbers over adjectives.

Read the full file on GitHub · 35 lines

Changes

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.

  1. 4d ago First seen · 35 lines · 0 tokens per session scan A f047486e90c1

Subscribe to this mod's changes

cursor is an agent published in the GitHub repository Byk3y/no-slop (10 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 545 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.