content_style_enforcement

A writing rule set for producing publishable essays, posts, documentation, marketing copy, and other content in a natural human voice.

In plain words
What is it for?
Reviewing and editing written content against a separate style guide before it is finalized.
Why use it?
It helps remove common AI-sounding phrases, vague corporate language, and other patterns that can make writing feel generic.

Cursor rule for Cursor

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/markmhendrickson/foundation/content_style_enforcement
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/foundation

Made for: Cursor.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,247 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 $0.00030 $0.01247
Opus 5 $0.00015 $0.00624
Sonnet 5 $0.00006 $0.00249
Haiku 4.5 $0.00003 $0.00125

Measured 2d ago against content hash 91238cbf9996, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content_style_enforcement 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 2d 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.

.cursor/rules/content_style_enforcement.mdc · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Style Enforcement Rule

Reference: foundation/conventions/writing_style_guide.md — Writing style guide

Ensures all content (essays, articles, posts, documentation) always follows anti-AI patterns and authentic human voice standards.

Trigger Patterns

When creating or editing ANY content:

  • Essays, articles, blog posts
  • Social media content
  • Documentation
  • Marketing copy
  • Technical writing
  • Any written content for publication

Agent Actions

Step 1: Load Style Guide

Before finalizing any content:

  1. Load foundation/conventions/writing_style_guide.md
  2. Review prohibited patterns
  3. Apply all style rules

Step 2: Apply Anti-AI Patterns

Before finalizing any content, MUST remove all AI-generated language patterns per the writing style guide:

Generic AI Phrases to Remove:

  • "Furthermore", "Moreover", "In addition"
  • "leverage" → use "use" or "draw on"
  • "empower" → use "enable" or "let"
  • "cutting-edge" → use specific technical terms
  • "revolutionary", "game-changing", "seamless" → remove marketing hype

Corporate Speak to Reduce:

  • "solution" → use specific description
  • "platform" → use "tool" or "system" where appropriate
  • "ecosystem" → use only when necessary, prefer specific names

Language Simplification:

  • "utilize" → "use"
  • "facilitate" → "enable" or "help"
  • "remembrances" → "memories"
  • "structural foundation" → "foundation"
  • Passive voice → Active voice ("it was found" → "I found")

Punctuation Patterns (AI-Generated Tendencies):

  • NEVER use em dashes (—) or en dashes (–)
  • Use commas for appositives and lists
  • Use periods to separate ideas
  • Use colons to introduce lists or explanations
  • Use standard hyphens (-) for compound words and ranges

Conversational Transitions (AI-Generated Tendencies):

  • NEVER use: "Now, let's...", "So, you might...", "Interestingly...", "As you can see...", "Keep in mind that..."
  • Use direct statements without transition words
  • Start with the subject directly

Soft Questions and Offers (AI-Generated Tendencies):

  • NEVER use: "Would you like to...?", "Have you considered...?", "Want to try...?", "Need help with...?"
  • Use direct instructions: "Use the store_record action to..."
  • Use declarative statements: "The system supports..."

Read the full file on GitHub · 138 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. 2d ago First seen · 138 lines · 30 tokens per session scan A 91238cbf9996

Subscribe to this mod's changes

content_style_enforcement is a cursor rule published in the GitHub repository markmhendrickson/foundation (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,247 once invoked, about $0.0002 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.