main

A rule system for a Cursor custom workflow that requires a Memory Bank—a collection of project notes—to exist before other work begins.

In plain words
What is it for?
It helps initialize projects and move through planning, design, implementation, review, and archiving while loading only the rules needed for each mode.
Why use it?
It ensures the agent has the required project context and follows the defined sequence of work modes.

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/alkoleft/mcp-bsl-platform-context/main
Clone the repo
git clone --depth 1 https://github.com/alkoleft/mcp-bsl-platform-context

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,423 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 $0.00000 $0.01423
Opus 5 $0.00000 $0.00711
Sonnet 5 $0.00000 $0.00285
Haiku 4.5 $0.00000 $0.00142

Measured 3d ago against content hash 87d33e5b0668, 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 3d 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

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 · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 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: This system is designed to work with Cursor custom modes, where each mode loads only the rules it needs. The system uses visual Mermaid diagrams and selective document loading to optimize context usage.

🧭 MODE-SPECIFIC VISUAL MAPS

graph TD
    subgraph Modes["Cursor Custom Modes"]
        VAN["VAN MODE<br>Initialization"] --> PLAN["PLAN MODE<br>Task Planning"]
        PLAN --> Creative["CREATIVE MODE<br>Design Decisions"]
        Creative --> Implement["IMPLEMENT MODE<br>Code Implementation"]
        Implement --> Reflect["REFLECT MODE<br>Task Review"]
        Reflect --> Archive["ARCHIVE MODE<br>Documentation"]
    end
    
    VAN -.->|"Loads"| VANRules["• main.md<br>• platform-awareness.md<br>• file-verification.md<br>• workflow-init.md"]
    PLAN -.->|"Loads"| PLANRules["• main.md<br>• task-tracking.md<br>• planning-process.md"]
    Creative -.->|"Loads"| CreativeRules["• main.md<br>• creative-phase.md<br>• design-patterns.md"]
    Implement -.->|"Loads"| ImplementRules["• main.md<br>• command-execution.md<br>• implementation-guide.md"]
    Reflect -.->|"Loads"| ReflectRules["• main.md<br>• reflection-format.md"]
    Archive -.->|"Loads"| ArchiveRules["• main.md<br>• archiving-guide.md"]

📋 MEMORY BANK VERIFICATION - MANDATORY IN ALL MODES

graph TD
    Start["Mode Activation"] --> CheckMemBank{"Memory Bank<br>Exists?"}
    
    CheckMemBank -->|"No"| CreateMemBank["CREATE MEMORY BANK<br>[CRITICAL STEP]"]
    CheckMemBank -->|"Yes"| VerifyMemBank["Verify Memory Bank<br>Structure"]
    
    CreateMemBank --> VerifyCreation{"Creation<br>Successful?"}
    VerifyCreation -->|"No"| AbortAll["⛔ ABORT ALL OPERATIONS<br>Fix Memory Bank First"]
    VerifyCreation -->|"Yes"| VerifyMemBank
    
    VerifyMemBank --> StructureCheck{"Structure<br>Valid?"}
    StructureCheck -->|"No"| FixStructure["Fix Memory Bank<br>Structure"]
    StructureCheck -->|"Yes"| ContinueMode["Continue with<br>Mode Operations"]
    
    FixStructure --> VerifyFix{"Fix<br>Successful?"}
    VerifyFix -->|"No"| AbortAll
    VerifyFix -->|"Yes"| ContinueMode
    
    style CheckMemBank fill:#ff0000,stroke:#990000,color:white,stroke-width:3px
    style CreateMemBank fill:#ff0000,stroke:#990000,color:white,stroke-width:3px
    style VerifyCreation fill:#ff0000,stroke:#990000,color:white,stroke-width:3px
    style AbortAll fill:#ff0000,stroke:#990000,color:white,stroke-width:3px
    style StructureCheck fill:#ff0000,stroke:#990000,color:white,stroke-width:3px
    style FixStructure fill:#ff5555,stroke:#dd3333,color:white
    style VerifyFix fill:#ff5555,stroke:#dd3333,color:white

Read the full file on GitHub · 156 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. 3d ago First seen · 156 lines · 0 tokens per session scan A 87d33e5b0668

Subscribe to this mod's changes

main is a cursor rule published in the GitHub repository alkoleft/mcp-bsl-platform-context (191 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,423 tokens. 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.