ai-assistant

Rules for configuring an AI assistant to work on the PoolAI project, including which documents to read and which tools and languages to use.

In plain words
What is it for?
Starting a new work session, locating active project guidance, following the Rust-first stack, and synchronizing concepts, status, and next steps.
Why use it?
They keep the assistant aligned with the project's current architecture, workflow, and session context.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/platinoff/poolai/ai-assistant
Clone the repo
git clone --depth 1 https://github.com/platinoff/poolAI

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01303
Opus 5 $0.00000 $0.00651
Sonnet 5 $0.00000 $0.00261
Haiku 4.5 $0.00000 $0.00130

Measured 2d ago against content hash 8c9b8556c41c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-assistant 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 2d 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/ai-assistant.mdc · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Assistant Rules

🧭 Подальша робота з чатом

При «налаштуйся для роботи з чатом» або старті нової сесії — спочатку читай chat-context.mdc. Там зведено: проект, ключові документи, термінал (MSYS2 only), git (без .sh), патчі, поточний стан і наступні кроки.


📚 Quick Reference - Key Documents for AI Assistant

⚠️ CRITICAL: Runtime stack (read first)

  • .cursor/rules/runtime-stack-policy.mdc — Rust primary; no Python runtime; JS UI + bash ops only.
  • Не пропонуй Python/sidecar/PyPI для ML чи API. Застарілі згадки в docs/archive/ — не канон.

⚠️ CRITICAL: Always check these documents first when answering questions

Main active documents (ALWAYS reference these):

  • Chat context (session start / «налаштуйся»): .cursor/rules/chat-context.mdc
  • Session handoff (кроки 1–12): docs/development/HANDOFF_NEW_SESSION.md
  • Autonomous run (orchestrator): newest docs/development/AUTO_RUN_SESSION_*.md (Post-Horizon: AUTO_RUN_SESSION_2026_POST_HORIZON.md)
  • Dev patterns registry: docs/development/AUTO_DEV_PATTERNS.md
  • Functionality manager (крок 12): docs/catalog/FUNCTION_MANAGEMENT.md §5.1; rule .cursor/rules/functionality-management.mdc
  • Orchestrator rule: .cursor/rules/autonomous-orchestrator.mdc
  • PRIMARY Concept: docs/concept/poolAI_concept_root.txt
  • Stable State: docs/status/STABLE_STATE_SUMMARY.md
  • Architect plan: docs/development/NEXT_STEPS_ARCHITECT_2026-03-17.md
  • Docs taxonomy: docs/STRUCTURE.md
  • Project README: README.md (in root)
  • Documentation Index: docs/README.md
  • Helper File: file_list.csv

When answering questions about:

  • Module status/completion: Check docs/status/PROJECT_STATUS_REPORT_2026-01-19.md FIRST
  • Development plans: Check docs/development/NEXT_STEPS_PLAN.md or latest NEXT_STEPS_*.md (для архітектурних стабілізацій — NEXT_STEPS_ARCHITECT_2026-03-17.md)
  • Project concept: Check docs/concept/poolAI_concept_root.txt FIRST (PRIMARY concept document)
  • Architecture: Check docs/status/PROJECT_STATUS_REPORT_2026-01-19.md and docs/concept/poolAI_concept_root.txt
  • Current progress: Check docs/status/PROJECT_STATUS_REPORT_2026-01-19.md
  • Next steps: Check docs/development/NEXT_STEPS_2026-01-19.md (і додатково — docs/development/NEXT_STEPS_ARCHITECT_2026-03-17.md для архітектурних покращень)

Read the full file on GitHub · 88 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. 2d ago First seen · 88 lines · 1,303 tokens per session scan A 8c9b8556c41c

Subscribe to this mod's changes

ai-assistant is a cursor rule published in the GitHub repository platinoff/poolAI (4 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,303 tokens. 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.