A project workflow that uses a shared Memory Bank, a set of files that preserve project context, across defined development phases. It provides commands for setup, planning, design, implementation, review, and archiving.

Use it to organize software work from initial project setup through planning, coding, review, and documentation.

It gives an AI coding assistant a repeatable process and helps keep decisions and progress available between tasks.

cursorrules — Cursor rule for Cursor by Zenobia000

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/Zenobia000/ai-agentic-coding-template_unified

agentmods

npx agentmods add rules/zenobia000/ai-agentic-coding-template_unified/cursorrules

Made for: Cursor.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/zenobia000/ai-agentic-coding-template_unified/cursorrules/github.svg)](https://agentmods.dev/rules/zenobia000/ai-agentic-coding-template_unified/cursorrules)

Your own site

<a href="https://agentmods.dev/rules/zenobia000/ai-agentic-coding-template_unified/cursorrules"><img src="https://agentmods.dev/badge/rules/zenobia000/ai-agentic-coding-template_unified/cursorrules/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/zenobia000/ai-agentic-coding-template_unified/cursorrules"><img src="https://agentmods.dev/badge/rules/zenobia000/ai-agentic-coding-template_unified/cursorrules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,355 This file is loaded in full into every session.

When invoked 4,355 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.04355	$0.04355
Opus 5.5	$0.01742	$0.01742
Sonnet 5.5	$0.00871	$0.00871
Haiku 4.5	$0.00436	$0.00436

Measured 1mo ago against content hash 25cebc777575, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

cursorrules — 100% identical, 0 lines differ

.ai/template/.cursorrules · 720 lines

How it starts

The opening of the file, as written. The whole thing — 720 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Universal AI Copilot Template

System Overview

This project uses the Universal AI Workflow System with Memory Bank for phased development workflow.

Core Principle: Memory Bank MUST be created and verified before any operations.

Project Information

Type: development-workflow
Tech Stack: markdown, yaml, javascript, python
Description: Universal AI copilot workflow template supporting multiple AI tools

Universal AI Commands

支援簡潔指令，與所有 AI 工具一致：

Workflow Commands (Phase Sequence)

/van → /plan → /creative → /implement → /reflect → /archive

Command	Description	Function
`/van`	初始化專案	Initialize project with Memory Bank creation
`/plan`	規劃任務	Task planning and WBS breakdown
`/creative`	設計架構	Design decisions and architecture planning
`/implement`	程式實作	Code implementation with progress tracking
`/reflect`	回顧總結	Task review and retrospective
`/archive`	文件歸檔	Documentation and knowledge preservation

System Commands

/commit: Generate a high-quality commit message.
/resume: Resume context from active state.

Memory Bank Structure

./memory-bank/
├── tasks.md           # Source of truth for all tasks
├── activeContext.md   # Current focus and active work
├── progress.md        # Implementation status
├── projectbrief.md    # Project overview and goals
├── techContext.md     # Technology stack and constraints
└── README.md          # Memory Bank documentation

If Memory Bank doesn't exist:

STOP all operations immediately
Run /van command to initialize
Wait for verification before proceeding

AI Behavior Guidelines

When User Runs Slash Commands

Verify Memory Bank first
- Check if ./memory-bank/ directory exists
- Verify required files are present
- If missing, guide user to run /van
Read relevant context
- Load tasks.md for current task list
- Load activeContext.md for current focus
- Load relevant files for design context

Read the full file on GitHub · 720 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.

1mo ago First seen · 720 lines · 4,355 tokens per session scan A 25cebc777575

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository Zenobia000/ai-agentic-coding-template_unified (7 stars, last pushed 8mo ago), licensed MIT. It adds 4,355 tokens to every session, about $0.0174 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.

Memory and context Planning

mempalace-recall-always

Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.

MemPalace/mempalace · 260 tokens

dreamd-recall

Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.

botzrDev/dreamd · 54 tokens

session-memory

Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.

major7apps/pensyve · 22 tokens

common_memory_bank

I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…

shalomeir/common-memory-bank · 1,801 tokens

self-improving-obsidian-llm-wiki

LLM Wiki OS operating rules.

Bahgs/Self-Improving-Obsidian-LLM-Wiki · 146 tokens

memsprout

Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.

memsprout/agents · 519 tokens