review-against-prose

review-against-prose is a cursor rule for Cursor from briangmilnes/APAS-VERUS. It costs 2,776 tokens per session, scanned A, original, MIT.

A review procedure for checking whether a chapter's Rust and Verus code matches its accompanying textbook prose. Verus is a Rust-based system for formally checking that code meets stated properties.

In plain words
What is it for?
Use it to review a named chapter, inventory its functions and prose requirements, examine algorithm costs and correctness claims, and report mismatches.
Why use it?
It provides a repeatable way to find missing implementations, weak specifications, proof gaps, incorrect cost claims, and textbook items not represented in code.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to review a named chapter, inventory its functions and prose requirements, examine algorithm costs and correctness claims, and report mismatches.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/briangmilnes/apas-verus/review-against-prose
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 review-against-prose

README.md
[![agentmods](https://agentmods.dev/badge/rules/briangmilnes/apas-verus/review-against-prose/github.svg)](https://agentmods.dev/rules/briangmilnes/apas-verus/review-against-prose)
Your own site
<a href="https://agentmods.dev/rules/briangmilnes/apas-verus/review-against-prose"><img src="https://agentmods.dev/badge/rules/briangmilnes/apas-verus/review-against-prose/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 review-against-prose

Your own site · 80×15
<a href="https://agentmods.dev/rules/briangmilnes/apas-verus/review-against-prose"><img src="https://agentmods.dev/badge/rules/briangmilnes/apas-verus/review-against-prose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,776 This file is loaded in full into every session.
When invoked 2,776 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 $0.02776 $0.02776
Opus 5 $0.01388 $0.01388
Sonnet 5 $0.00555 $0.00555
Haiku 4.5 $0.00278 $0.00278

Measured 10d ago against content hash aab43a70ac41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-against-prose 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 10d 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/apas-verus/review-against-prose.mdc · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Chapter Against Prose

When the user says "review ChapNN" or "review against prose":

Phase 1: Inventory (tool-generated)

Run veracity to generate the function inventory and spec strengths:

~/projects/veracity/target/release/veracity-review-module-fn-impls -d src/ChapNN

Then classify spec strengths per the classify-spec-strengths rule. This gives us:

  • Every function in the chapter
  • Whether it's in a trait, impl, or module-level
  • Whether it's inside verus!
  • Spec strength (strong / partial / weak / none)
  • Proof holes

This is the mechanical baseline. Don't duplicate what the tool already produces.

Phase 2: Prose Inventory (manual)

Read prompts/ChapNN.txt. Extract every named item into categories:

  • Definitions: Named ADTs, type classes, abstract interfaces
  • Algorithms: Pseudocode with a name (e.g., "Algorithm 21.1", "insertion sort")
  • Cost specs: Every stated Work and Span bound
  • Theorems/Properties: Correctness claims, invariants, bounds
  • Exercises/Problems: Numbered items that the code may implement

Phase 3: Algorithmic Analysis (the review)

For each executable function (fn, not spec fn or proof fn):

3a. Cost annotations in source

Write two doc comment lines directly before the function:

/// - APAS: Work Θ(...), Span Θ(...)
/// - Claude-Opus-4.6: Work Θ(...), Span Θ(...) — [reason if different]

Rules for the two lines:

APAS line: What the textbook says the cost should be for this algorithm. If the prose doesn't state a cost for this specific function, write:

/// - APAS: (no cost stated)

If the function has no prose counterpart at all, write:

/// - APAS: N/A — Verus-specific scaffolding.

Claude-Opus-4.6 line: What the code actually achieves, based on reading the implementation. Three outcomes:

  1. Agree: /// - Claude-Opus-4.6: Work Θ(...), Span Θ(...) — agrees with APAS.
  2. Disagree: /// - Claude-Opus-4.6: Work Θ(...), Span Θ(...) — [specific reason for difference]
  3. Cannot determine: /// - Claude-Opus-4.6: Cost not analyzable — [reason, e.g., external_body]

Read the full file on GitHub · 282 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. 10d ago First seen · 282 lines · 2,776 tokens per session scan A aab43a70ac41

Subscribe to this mod's changes

review-against-prose is a cursor rule published in the GitHub repository briangmilnes/APAS-VERUS (10 stars, last pushed 1mo ago), licensed MIT. It adds 2,776 tokens to every session, about $0.0139 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.