poolai-session-iteration

A set of project rules for running PoolAI development in repeated work sessions, using MSYS2, the S: drive, Git, and Rust tools.

In plain words
What is it for?
Starting a PoolAI session, checking the workspace and disk, cleaning Rust build files, and recording what the next session should do.
Why use it?
It keeps each session focused on one planned work item and provides handoff notes for the next session. It also helps avoid running out of disk space during builds.

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/poolai-session-iteration
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 5,766 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 $0.05766
Opus 5 $0.00000 $0.02883
Sonnet 5 $0.00000 $0.01153
Haiku 4.5 $0.00000 $0.00577

Measured 2d ago against content hash e329d3c25ee4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

poolai-session-iteration 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/poolai-session-iteration.mdc · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ітераційна сесія PoolAI

Ролі — poolai-agent-roles.mdc. Workflow — virtual-development-team.mdc.

Одна сесія = один PH-S*

Правило Дія
Черга спринтів FM §5.12 (журнал PH-S*) + NEXT_SESSION_PROMPT.md
Черга FM-* FM §5.1джерело пріоритетів для project scan
Scope Лише файли поточного PH-S*; не повторювати з блоку «Не повторювати» у NEXT_SESSION
Завершення PH-S* → ✅ §5.12 + HANDOFF + NEXT_SESSION → наступний PH-S*

S0

Спочатку диск (до cargo / scan / drain), потім git + docs.

  1. Диск S: df -h /s | tail -1 + bash scripts/check_target_disk.sh
    • avail <5G або check_target_disk warn → cargo clean (за потреби повторно df / check)
    • avail <12G або target/ роздутий → clean / зменшити тиск перед важкими збірками
  2. MSYS2: git fetch; git status -sb; git log -1 --oneline
  3. HANDOFF_NEW_SESSION.md · FM §5.12 · NEXT_SESSION_PROMPT.md
export PATH="$HOME/.cargo/bin:/ucrt64/bin:/usr/bin:$PATH"
export K8S_OPENAPI_ENABLED_VERSION=1.28
export CARGO_TARGET_DIR=/s/rust/poolAI/target
cd /s/rust/poolAI || cd "S:/rust/poolAI"
df -h /s | tail -1
bash scripts/check_target_disk.sh
# за потреби: cargo clean && df -h /s | tail -1

Тести (Rust-first)

Див. poolai-testing-policy.mdc.

Scope Команда
API / grid / job / telegram wire cargo fmt --allcargo test-ci (+ openapi-gap після API)
Admin UI / axe / visual + bash bin/e2e-playwright.sh --start (PATH обов’язково з /ucrt64/bin)
Новий PH-S* API-only tests/*_integration.rs, не новий Playwright spec

Shell

PowerShell для git/cargo C:\msys64\usr\bin\bash.exe -lc '…' або зовнішнє MSYS2
git у Cursor для push Зовнішнє MSYS2 (менше index.lock)

Після src/ / tests/ / crates/: cargo fmt --allcargo test-ci.

Read the full file on GitHub · 258 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 · 258 lines · 0 tokens per session scan A e329d3c25ee4

Subscribe to this mod's changes

poolai-session-iteration 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 5,766 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.