cursor

A set of writing and coding rules that makes generated text sound less like it came from an AI assistant.

In plain words
What is it for?
Use it when creating or editing documentation, messages, code, and other text that should follow specific style rules.
Why use it?
It reduces repetitive sentence patterns, vague claims, and other writing habits that can make code comments or prose feel artificial.

Cursor rule

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 rules/hugolopes45/llmstrip/cursor
Clone the repo
git clone --depth 1 https://github.com/HugoLopes45/llmstrip
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,134 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 $0.00009 $0.01134
Opus 5 $0.00005 $0.00567
Sonnet 5 $0.00002 $0.00227
Haiku 4.5 $0.00001 $0.00113

Measured yesterday against content hash c747e6cf4a66, 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 yesterday.

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.

prompts/cursor.mdc · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When writing or editing code and text, follow these rules to avoid AI-sounding patterns. This applies both when generating new content and when asked to edit or review existing content.

Prevention: do not generate these patterns

Prose — structural

Sentence level

  • Vary sentence length. Include at least one sentence under 8 words per paragraph.
  • Start sentences with subject-verb. No more than 2 sentences per paragraph may open with "By", "Through", "In", "With", "Having", or "Moving".
  • Sentences may start with "And", "But", or "So".
  • One sentence, one action. Break compound sentences joined by "while maintaining", "ensuring that", "that enables".
  • No "not only X but also Y", "both X and Y", "everything from X to Y" — state items directly.

Paragraph level

  • No mini-essay structure: thesis sentence → evidence → forward projection. Start with the first concrete fact.
  • Never end a paragraph with a vague forward-looking statement. If the plan is real, name a date.
  • No self-congratulation framing: "worked diligently", "through careful planning", "we've created a solution that positions us".

Word and phrase level — never use tapestry, testament, delve, underscore, pivotal, comprehensive, multifaceted, evolving landscape, vibrant, crucial, moreover, furthermore, in conclusion, serves as a reminder, stands as a testament, ingrained, indelible, leveraging, seamlessly, robust (use "solid"), cutting-edge, revolutionary, innovative (use "new"), groundbreaking, streamline, utilize (use "use"), facilitate (use a simpler verb), endeavor, commence (use "start"), subsequently (use "then"), it is worth noting, it is important to note, notably, diligently, spearheaded, meticulous (use "careful"), profound impact, iterative refinement, security posture, positions us well, truly excels, further strengthen, moving forward (unless followed by a date), going forward, established (use "set up"), maintained (use "kept"), ensured (use "checked")

Filler — never write these

  • "in order to" (use "to")
  • "due to the fact that" (use "because")
  • "it is worth noting that"
  • "it is important to note that"
  • "it should be noted that"
  • "at the end of the day"
  • "with that said"
  • "in terms of" (name the specific aspect)
  • "a wide range of" (list what is included, or say "many")
  • "play a crucial role" (name the role or delete)

Read the full file on GitHub · 92 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. yesterday First seen · 92 lines · 9 tokens per session scan A c747e6cf4a66

Subscribe to this mod's changes

cursor is a cursor rule published in the GitHub repository HugoLopes45/llmstrip (11 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 1,134 once invoked, about $0.0000 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 2026-08-30.