optimization-integration

An integration guide for a Memory Bank, a set of project notes an agent uses to retain context between tasks. It describes how different context and workflow improvements fit together.

In plain words
What is it for?
Use it when setting up or changing rule loading, task complexity handling, context management, workflow transitions, and project documentation.
Why use it?
It helps keep these improvements coordinated instead of applying separate rules that conflict or leave gaps.

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/platform-context-exporter/optimization-integration
Clone the repo
git clone --depth 1 https://github.com/alkoleft/platform-context-exporter

Made for: Cursor.

Per session 2,319 This file is loaded in full into every session.
When invoked 2,319 The same file — it is already loaded in full.
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 $0.02319 $0.02319
Opus 5 $0.01159 $0.01159
Sonnet 5 $0.00464 $0.00464
Haiku 4.5 $0.00232 $0.00232

Measured 2d ago against content hash b750aab3f916, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimization-integration 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.

Origin

This is a copy

100% identical to optimization-integration — 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/Core/optimization-integration.mdc · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.


description: Integration hub for Memory Bank optimizations globs: "/optimization*/", "/integration*/" alwaysApply: false

MEMORY BANK OPTIMIZATION INTEGRATION

TL;DR: This file serves as the integration point for all Memory Bank optimizations, coordinating the various optimization components to work seamlessly together.

🔄 OPTIMIZATION INTEGRATION FLOW

graph TD
    Start["Memory Bank<br>Initialization"] --> HRL["Hierarchical<br>Rule Loading"]
    HRL --> ACM["Adaptive<br>Complexity Model"]
    ACM --> DCM["Dynamic<br>Context Management"]
    DCM --> TMO["Transition<br>Optimization"]
    
    subgraph "Level-Specific Optimizations"
        L1["Level 1<br>Optimizations"]
        L2["Level 2<br>Optimizations"]
        L3["Level 3<br>Optimizations"]
        L4["Level 4<br>Optimizations"]
    end
    
    ACM --> L1 & L2 & L3 & L4
    
    L1 & L2 & L3 & L4 --> CPO["Creative Phase<br>Optimization"]
    
    CPO --> PDO["Progressive<br>Documentation"]
    TMO --> PDO
    
    PDO --> MBO["Memory Bank<br>Optimization"]
    
    style Start fill:#4da6ff,stroke:#0066cc,color:white
    style HRL fill:#ffa64d,stroke:#cc7a30,color:white
    style ACM fill:#4dbb5f,stroke:#36873f,color:white
    style DCM fill:#d94dbb,stroke:#a3378a,color:white
    style TMO fill:#4dbbbb,stroke:#368787,color:white
    style CPO fill:#e699d9,stroke:#d94dbb,color:white
    style PDO fill:#d971ff,stroke:#a33bc2,color:white
    style MBO fill:#ff71c2,stroke:#c23b8a,color:white

📋 OPTIMIZATION COMPONENT REGISTRY

// Optimization component registry pseudocode
const optimizationRegistry = {
  // Core optimizations
  hierarchicalRuleLoading: {
    file: "Core/hierarchical-rule-loading.mdc",
    dependencies: [],
    priority: 1
  },
  adaptiveComplexityModel: {
    file: "main-optimized.mdc",
    dependencies: ["hierarchicalRuleLoading"],
    priority: 2
  },
  modeTransitionOptimization: {
    file: "Core/mode-transition-optimization.mdc",
    dependencies: ["hierarchicalRuleLoading", "adaptiveComplexityModel"],
    priority: 3
  },
  
  // Level-specific optimizations
  level1Optimization: {
    file: "Level1/optimized-workflow-level1.mdc",
    dependencies: ["adaptiveComplexityModel"],
    priority: 4
  },
  
  // Feature-specific optimizations
  creativePhaseOptimization: {
    file: "Phases/CreativePhase/optimized-creative-template.mdc",
    dependencies: ["hierarchicalRuleLoading", "adaptiveComplexityModel"],
    priority: 5
  }
};

Read the full file on GitHub · 321 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 · 321 lines · 2,319 tokens per session scan A b750aab3f916

Subscribe to this mod's changes

optimization-integration is a cursor rule published in the GitHub repository alkoleft/platform-context-exporter (48 stars, last pushed 1y ago), licensed MIT. It adds 2,319 tokens to every session, about $0.0116 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to optimization-integration, differing in 0 lines, and is treated as a copy.