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/platinoff/poolAIWrote 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/platinoff/poolai/rust-architect)<a href="https://agentmods.dev/rules/platinoff/poolai/rust-architect"><img src="https://agentmods.dev/badge/rules/platinoff/poolai/rust-architect/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/platinoff/poolai/rust-architect"><img src="https://agentmods.dev/badge/rules/platinoff/poolai/rust-architect.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 | $0.03367 | $0.03367 |
| Opus 5.5 | $0.01347 | $0.01347 |
| Sonnet 5.5 | $0.00673 | $0.00673 |
| Haiku 4.5 | $0.00337 | $0.00337 |
Grade A, and why
rust-architect 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 1mo 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Architect Rules - PoolAI Development
⛔ Runtime stack (non-negotiable)
- Product: Rust only (
src/,tests/,crates/). Admin UI:src/ui/(JavaScript). E2E:e2e/(TypeScript). - No Python in runtime, ML, or API layers. Do not cite archived docs that suggest Python sidecars.
- Dev audit:
cargo run --bin poolai-openapi-gap-audit— OpenAPI vs Axum routes (src/bin/poolai_openapi_gap_audit.rs). - Full policy:
.cursor/rules/runtime-stack-policy.mdc(alwaysApply).
🏗️ Rust Architect Workflow
⚠️ Термінал: канонічно MSYS2 bash; автоматизація — з контекстом
Для людини (git push, довгі збірки, уникнення index.lock / CreateFileMapping на Windows)
Terminal: C:\msys64\usr\bin\bash.exe — зовнішнє вікно MSYS2 UCRT64 (див. .cursor/commands/git-push.md).
Environment: rust-toolchain.toml — канал 1.92.0, ціль x86_64-pc-windows-gnu + компоненти rustfmt, clippy. Якщо rustup show показує MSVC у каталозі репо, вирівняй toolchain: rustup override set 1.92.0-x86_64-pc-windows-gnu у корені репо (або збірка в UCRT64 за README).
Локальні перевірки (cargo test, fmt, clippy) — у тому ж MSYS2 bash, що й git (див. блок у git-push.md). GitHub Actions працює на власному раннері; це не привід використовувати PowerShell/cmd у цьому репо.
Windows 11 (збірки 26100+, зокрема 26200): за гальмування збірок — перевірити сканування target/ (Defender); при нестачі місця — cargo clean або винести артефакти через CARGO_TARGET_DIR.
target/ і ліміт дискового простору
Щоб не переповнювався диск і не падали лінкер / тести через ENOSPC або фрагментацію вільного місця:
- Політика (м’які пороги за замовчуванням): тримати ≥ 12 GiB вільних на томі, де лежить репозиторій (або
CARGO_TARGET_DIR); каталогtarget/доречно тримати ≤ ~48 GiB для цього монорепо — інакшеcargo cleanабо окремий том підCARGO_TARGET_DIR. - Перевірка перед важкими прогонами:
bash scripts/check_target_disk.sh(лише попередження) або з жорстким фейлом:bash scripts/check_target_disk.sh --enforce/POOLAI_ENFORCE_DISK_LIMIT=1. Пороги:POOLAI_MIN_FREE_DISK_GB,POOLAI_MAX_TARGET_DIR_GB(див. шапку скрипта). - Зменшення тиску на диск:
CARGO_INCREMENTAL=0для разових повних матриць;-j 1для лінкера на Windows (уже в доках); не тримати одночасно кілька величезнихtarget/на одному томі.
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.
- 1mo ago First seen · 211 lines · 3,367 tokens per session scan A 9357ff3b9c28
rust-architect is a cursor rule published in the GitHub repository platinoff/poolAI (4 stars, last pushed yesterday), licensed MIT. It adds 3,367 tokens to every session, about $0.0135 per session on Opus 5.5. 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
rust-module-refactor
Use when splitting Rust modules, moving tests, tightening visibility, or preserving facades during refactors.
table-of-contents-standard
Standard section ordering and TOC format for Verus source files.
arc-deref-pattern
When implementing parallel (Mt) algorithms in Verus, do NOT assume.
wrap-vs-specify
When to use externaltypespecification vs wrapper struct for Verus specs.
core
Core STT/TTS abstraction layer documentation.
spec-fn-naming
Spec function naming conventions.