main

A master rule file that controls an AI coding workflow through stages such as setup, planning, implementation, review, and archiving.

In plain words
What is it for?
Use it to coordinate slash commands—commands typed with a leading slash in Cursor's AI chat—and enforce the project's shared workflow. It also defines how the memory files support work across stages.
Why use it?
It ensures the project memory system is checked before work begins and keeps development steps organized.

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/zenobia0000/cursor-agentic-coding-template/main
Clone the repo
git clone --depth 1 https://github.com/Zenobia0000/cursor-agentic-coding-template

Made for: Cursor.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,814 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00018 $0.01814
Opus 5 $0.00009 $0.00907
Sonnet 5 $0.00004 $0.00363
Haiku 4.5 $0.00002 $0.00181

Measured yesterday against content hash 48e752f0938f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

main 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 yesterday.

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

This is a copy

100% identical to main — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/rules/isolation_rules/main.mdc · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🔍 ISOLATION-FOCUSED MEMORY BANK SYSTEM

🚨 CRITICAL RULE: MEMORY BANK CREATION IS MANDATORY 🚨 Memory Bank MUST be created BEFORE any other operation in ANY mode NO process can continue without verifying Memory Bank existence

TL;DR (Updated 2025): This system uses Cursor's Custom Slash Commands (.cursor/commands/) to implement a phased workflow. Each command (/van, /plan, /creative, /implement, /reflect, /archive) represents a distinct development phase with specific responsibilities. The system uses visual Mermaid diagrams and Memory Bank files to maintain context between phases.

📢 IMPORTANT UPDATE (2025)

Custom Modes → Custom Slash Commands

Cursor has replaced "Custom Modes" with "Custom Slash Commands" in 2025. This system has been updated accordingly:

  • Before (2024): Custom Modes in Settings → Features → Chat
  • Now (2025): Custom Slash Commands in .cursor/commands/ directory
  • How to Use: Type /van, /plan, /creative, /implement, /reflect, or /archive in Cursor AI chat
  • Rules Still Apply: .cursor/rules/ directory continues to define project-wide rules

🧭 SLASH COMMAND WORKFLOW MAP

graph TD
    subgraph Commands["Cursor Custom Slash Commands"]
        VAN["/van<br>Initialization"] --> PLAN["/plan<br>Task Planning"]
        PLAN --> Creative["/creative<br>Design Decisions"]
        Creative --> Implement["/implement<br>Code Implementation"]
        Implement --> Reflect["/reflect<br>Task Review"]
        Reflect --> Archive["/archive<br>Documentation"]
    end
    
    VAN -.->|"Command File"| VANCmd[".cursor/commands/van.md"]
    PLAN -.->|"Command File"| PLANCmd[".cursor/commands/plan.md"]
    Creative -.->|"Command File"| CreativeCmd[".cursor/commands/creative.md"]
    Implement -.->|"Command File"| ImplementCmd[".cursor/commands/implement.md"]
    Reflect -.->|"Command File"| ReflectCmd[".cursor/commands/reflect.md"]
    Archive -.->|"Command File"| ArchiveCmd[".cursor/commands/archive.md"]
    
    VANCmd -.->|"References"| Rules["Project Rules<br>.cursor/rules/"]
    PLANCmd -.->|"References"| Rules
    CreativeCmd -.->|"References"| Rules
    ImplementCmd -.->|"References"| Rules
    ReflectCmd -.->|"References"| Rules
    ArchiveCmd -.->|"References"| Rules

Read the full file on GitHub · 180 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. yesterday First seen · 180 lines · 18 tokens per session scan A 48e752f0938f

Subscribe to this mod's changes

main is a cursor rule published in the GitHub repository Zenobia0000/cursor-agentic-coding-template (5 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 1,814 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to main, differing in 0 lines, and is treated as a copy.