WRITING-STYLE

A set of writing rules for messages, issue-tracker comments, documentation, reports, and investigation findings.

In plain words
What is it for?
Use it to guide the tone, sentence length, evidence use, punctuation, and wording of written project output.
Why use it?
It keeps writing factual, professional, concise, and free of common AI-style wording or unsupported claims.

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/qwickapps/ai-sdlc-workflows/writing-style
Clone the repo
git clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflows

Made for: Cursor.

Per session 1,107 This file is loaded in full into every session.
When invoked 1,107 The same file — it is already loaded in full.
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 $0.01107 $0.01107
Opus 5 $0.00553 $0.00553
Sonnet 5 $0.00221 $0.00221
Haiku 4.5 $0.00111 $0.00111

Measured 2d ago against content hash d7103dd6209e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

WRITING-STYLE 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/.cursor/rules/WRITING-STYLE.mdc · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Style Rules

When to apply: Before writing any output to user, JIRA comments, documentation, reports, or spike findings.


Core Principles

  1. Professional and human-like - Write like a senior engineer, not an AI
  2. Neutral tone - Objective, factual, no excessive enthusiasm
  3. Short sentences - One idea per sentence
  4. Evidence-based - Every claim needs a source
  5. No AI markers - Avoid patterns that signal AI-generated content

Reference: See COMMON-PATTERNS.md § Evidence Requirements for claim documentation.


Prohibited Elements

Never Use:

  • Emojis (🚫 ✅ ⚠️) - Use plain text instead
  • Excessive punctuation (!!!, ???)
  • Excessive em dashes (—) - Prefer periods or semicolons
  • Superlatives without evidence ("amazing", "incredible", "revolutionary")
  • Validation language ("You're absolutely right", "Great question")
  • AI phrases ("I apologize for the confusion", "Let me clarify")

Use Instead:

Prohibited Use Instead
🚫 BLOCKER BLOCKER (plain text)
Amazing discovery! Found X in file Y
You're absolutely right Correct
I apologize for... (Just fix it)
Let me clarify... (Just state it clearly)

Required Elements

Every Claim Needs:

  • Source: File:line, URL, command output
  • Evidence: Code snippet, quote, data
  • Verification method: How verified

Bad:

The app may have around 20 plugins that possibly need attention.

Good:

The app has 29 Cordova plugins (package.json:65-107).
9 Apache verified, 7 private forks, 13 community plugins.

Reference: See FACT-VERIFICATION.md for verification requirements and COMMON-PATTERNS.md § Evidence Requirements for format.


Sentence Structure

Prefer Short Sentences:

Bad:

The migration is complex and will require significant changes to hooks, plugins, and custom patches, but it's feasible if we allocate proper resources and follow the phased approach.

Read the full file on GitHub · 176 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 · 176 lines · 1,107 tokens per session scan A d7103dd6209e

Subscribe to this mod's changes

WRITING-STYLE is a cursor rule published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,107 tokens to every session, about $0.0055 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.