A project rule for using a memory-bank/ folder as structured project memory. Before working, the agent must read specified context files and follow a staged workflow from task definition through building and archiving.

Guiding coding work through van, plan, creative, build, reflect, and archive stages; reading project context; and protecting unrelated task sections in shared memory files.

It gives the agent project context before it changes code and helps keep work organized across tasks. It also defines where to look first for component maps, patterns, plans, and code relationships.

cursorrules — Cursor rule by ReSkin-Games

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/reskin-games/memorybank-plus/cursorrules

Clone the repo

git clone --depth 1 https://github.com/ReSkin-Games/memorybank-plus

Made for: Cursor.

Per session 413 This file is loaded in full into every session.

When invoked 413 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00413	$0.00413
Opus 5	$0.00206	$0.00206
Sonnet 5	$0.00083	$0.00083
Haiku 4.5	$0.00041	$0.00041

Measured 2d ago against content hash e741c180dbf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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.

template/rules/.cursorrules · 33 lines

What it actually says

Memory Bank workflow

В корне проекта есть memory-bank/ — структурированная память. Перед задачей прочитай:

memory-bank/README.md (один раз за сессию)
memory-bank/tasks.md (активные задачи)
memory-bank/activeContext.md (текущий фокус)

Workflow задачи

/van → /plan → /creative → /build → /reflect → /archive

L1 (фикс): /van → /build → /archive
L2 (улучшение): /van → /plan → /build → /reflect → /archive
L3 (фича): /van → /plan → /creative → /build → /reflect → /archive
L4 (система): полный цикл + фазная реализация

Дисциплина чтения

Перед Glob/Grep/Read по src/ — сначала memory-bank/docs/component-map.md.
Для system-patterns/ и style-guide/ — сначала _index.md, потом точечно.
Для plans/, archive/, reflection/ — не читай пачкой. Только конкретный файл.
codegraph (если установлен): структурные вопросы «где символ / кто вызывает» — у графа (codegraph_* / memory-bank/codegraph/graph.json) до grep. Лид, не пруф — blast-radius проверяй в коде.

Параллельная работа

В shared-файлах memory-bank/ блоки разных задач защищены HTML-маркерами . Чужие блоки не трогай. Пиши только в свой.

Edit > Write

Для shared-файлов memory-bank/ (tasks.md, activeContext.md, progress.md, projectbrief.md, productContext.md, techContext.md) — только Edit, никогда Write.

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.

2d ago First seen · 33 lines · 413 tokens per session scan A e741c180dbf2

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository ReSkin-Games/memorybank-plus (7 stars, last pushed 3mo ago), licensed MIT. It adds 413 tokens to every session, about $0.0021 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.

Memory and context Planning Productivity ai-agents claude-code codex cursor developer-tools installer

cursor

You are working on the checkout service. Preserve transaction integrity and auditability.

mrwogu/promptscript · 53 tokens

beanstalk-deploy

Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.

pr-pm/prpm · 0 tokens

creating-kiro-agents

Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.

pr-pm/prpm · 0 tokens

archcore-files

Enforce MCP-only operations when working with .archcore/ files.

archcore-ai/plugin · 0 tokens

frontend-architecture

Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.

louisbrulenaudet/monorepo-template · 0 tokens

test-plan

Plan Katalon True Platform/TestOps testing for a release, sprint, or feature. Use when you need to translate quality goals into scope, prioritize testing by requirement coverage and risk, decide what to test first, or build the executable plan structure (folders, suites, and sprint/release association) that stands in…

katalon-labs/true-skills · 137 tokens