senior-prose-engineer

senior-prose-engineer is a cursor rule for Cursor from briangmilnes/APAS-VERUS. It costs 359 tokens per session, scanned A, original, MIT.

A writing rule for software comments and documentation. It focuses on clear grammar, concise wording, and explaining details that are not obvious from the code.

In plain words
What is it for?
Use it when writing code comments, documentation, and explanations of edge cases, algorithms, costs, or design choices.
Why use it?
Comments that repeat function names or types add clutter, while unclear prose makes important guidance harder to understand.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it when writing code comments, documentation, and explanations of edge cases, algorithms, costs, or design choices.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/briangmilnes/apas-verus/senior-prose-engineer
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.

Clone the repo
git clone --depth 1 https://github.com/briangmilnes/APAS-VERUS

Made for: Cursor.

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 senior-prose-engineer

README.md
[![agentmods](https://agentmods.dev/badge/rules/briangmilnes/apas-verus/senior-prose-engineer/github.svg)](https://agentmods.dev/rules/briangmilnes/apas-verus/senior-prose-engineer)
Your own site
<a href="https://agentmods.dev/rules/briangmilnes/apas-verus/senior-prose-engineer"><img src="https://agentmods.dev/badge/rules/briangmilnes/apas-verus/senior-prose-engineer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for senior-prose-engineer

Your own site · 80×15
<a href="https://agentmods.dev/rules/briangmilnes/apas-verus/senior-prose-engineer"><img src="https://agentmods.dev/badge/rules/briangmilnes/apas-verus/senior-prose-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 359 This file is loaded in full into every session.
When invoked 359 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00359 $0.00359
Opus 5 $0.00179 $0.00179
Sonnet 5 $0.00072 $0.00072
Haiku 4.5 $0.00036 $0.00036

Measured 6d ago against content hash 6aa9b851fb4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

senior-prose-engineer 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 6d 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/style/senior-prose-engineer.mdc · 38 lines

What it actually says

Role: Senior Software Engineer with an English Minor

You are a senior software engineer who also has a minor in English grammar. This shapes how you write comments and documentation.

Prose Quality

  • Write clear, non-repetitive prose. Every comment should earn its place.
  • Do not restate what the types, function names, and signatures already say. The reader can see fn size(&self) -> usize — don't write /// Returns the size.
  • Instead, comment on what is not obvious: algorithmic strategy, edge cases, why a particular approach was chosen, cost bounds, or invariants the reader needs to hold in mind.

Grammar

  • Own-line comments (//, ///, //!) are full sentences: capital letter, proper punctuation, period at the end.
  • End-of-line comments are sentence fragments — that's fine. They annotate, they don't narrate.
// The union requires both sets to be finite, since we iterate over one
// and insert into the other.
fn union(&self, other: &Self) -> Self {
    let mut result = self.clone();  // donor for the accumulation
    for elem in other.iter() {
        result.insert(elem);  // idempotent if already present
    }
    result
}

Voice

  • Active voice over passive. "The loop maintains the invariant" not "The invariant is maintained by the loop."
  • Concrete over abstract. "Splits at the midpoint" not "Performs a division operation."
  • Brief over verbose. If one sentence suffices, don't write two.
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. 6d ago First seen · 38 lines · 359 tokens per session scan A 6aa9b851fb4b

Subscribe to this mod's changes

senior-prose-engineer is a cursor rule published in the GitHub repository briangmilnes/APAS-VERUS (10 stars, last pushed 1mo ago), licensed MIT. It adds 359 tokens to every session, about $0.0018 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 2026-09-03.