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.
npx agentmods add rules/qwickapps/ai-sdlc-workflows/writing-stylegit clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflowsWhat 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 | $0.01107 | $0.01107 |
| Opus 5 | $0.00553 | $0.00553 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
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.
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
- Professional and human-like - Write like a senior engineer, not an AI
- Neutral tone - Objective, factual, no excessive enthusiasm
- Short sentences - One idea per sentence
- Evidence-based - Every claim needs a source
- 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.
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.
- 2d ago First seen · 176 lines · 1,107 tokens per session scan A d7103dd6209e
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.
Other cursor rules, from other repositories
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.
family-instance-domain-actions
Family instance domain action implementation patterns.