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/run-verus)<a href="https://agentmods.dev/rules/briangmilnes/apas-verus/run-verus"><img src="https://agentmods.dev/badge/rules/briangmilnes/apas-verus/run-verus/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/run-verus"><img src="https://agentmods.dev/badge/rules/briangmilnes/apas-verus/run-verus.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 | $0.00388 | $0.00388 |
| Opus 5 | $0.00194 | $0.00194 |
| Sonnet 5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
run-verus 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 5d 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.
What it actually says
Running Verus
Always use the shell scripts. Do not type raw verus commands.
scripts/validate.sh
Use this when:
- Checking if code verifies
- After making changes to proofs or implementations
- Before committing changes
See validate.mdc for dev_only and experiments_only modes.
Important
- Never use
cargo verus,cargo build, or any cargo-based compilation for verification. - Verus includes its own vstd automatically — do not pass
-L dependency,--extern vstd, or any library paths. - There is no need for
target/debug/ortarget/release/directories for verification. Verus manages its own dependencies.
Output Display
Always show the full output from verus verification:
- Use
head -100to limit to 100 lines if needed - Never use
grepto filter verus output - Show complete verification results including all errors and warnings
- Always echo the output into your response text as a markdown code block - do not rely on the terminal widget which collapses output
Logs
All three scripts (validate.sh, rtt.sh, ptt.sh) log to logs/ with timestamped
filenames (e.g., logs/validate.20260321-073354.log). To review the last run without
re-executing:
ls -t logs/validate.*.log | head -1 | xargs cat
ls -t logs/rtt.*.log | head -1 | xargs cat
ls -t logs/ptt.*.log | head -1 | xargs cat
Read the log file to diagnose failures rather than re-running the suite.
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.
- 5d ago First seen · 49 lines · 388 tokens per session scan A a39cc96d7e11
run-verus is a cursor rule published in the GitHub repository briangmilnes/APAS-VERUS (10 stars, last pushed 1mo ago), licensed MIT. It adds 388 tokens to every session, about $0.0019 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.
Other cursor rules, from other repositories
core
Core STT/TTS abstraction layer documentation.
rust-architect
PoolAI — Rust Architect workflow: runtime stack, MSYS2, target/ disk, pre-push checks, docs sync.
rust-module-refactor
Use when splitting Rust modules, moving tests, tightening visibility, or preserving facades during refactors.
rust-development-standards
Rust development standards: idioms, style, anti-patterns (Rust 2021 edition, 2024 where applicable).
ivolgaql-project
General development rules for ИволгаQL, an early-stage Rust project with a command-line and TCP server interface. They define the project structure, Russian user experience, coding conventions, testing, builds, and commit-message format.
rust-native-architecture
Enforces native-first architecture and crate boundary rules for the nca workspace.