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.
git clone --depth 1 https://github.com/briangmilnes/APAS-VERUSWrote 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.
[](https://agentmods.dev/rules/briangmilnes/apas-verus/review-against-prose)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- Agree:
/// - Claude-Opus-4.6: Work Θ(...), Span Θ(...) — agrees with APAS. - Disagree:
/// - Claude-Opus-4.6: Work Θ(...), Span Θ(...) — [specific reason for difference] - Cannot determine:
/// - Claude-Opus-4.6: Cost not analyzable — [reason, e.g., external_body]
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.
- 10d ago First seen · 282 lines · 2,776 tokens per session scan A aab43a70ac41
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.
Other cursor rules, from other repositories
clean-code-reviewer
Eliminates technical debt using SOLID, DRY, YAGNI, and Addy Osmani production-grade engineering principles. / TR: SOLID, DRY, YAGNI ve Addy Osmani üretim seviyesi mühendislik ilkeleri ile kod kalitesini denetleyen yetenek.
sweep-benchmarks
Audit xrspatial modules for asv benchmark coverage gaps: missing benchmarks, backend parameterization gaps, unrepresentative inputs, broken or silently-skipped benchmarks.
code-review
BMAD BMM Agent: code-review.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.