memory-context-optimization

A set of rules for giving coding agents focused, precise instructions and using their conversation space efficiently.

In plain words
What is it for?
Use it to structure bug reports and coding tasks, provide relevant context, group related work, and keep separate tasks organized.
Why use it?
It reduces wasted context, repeated explanations, and unclear requests that can lead to the wrong code changes.

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/sethdford/flowx/memory-context-optimization
Clone the repo
git clone --depth 1 https://github.com/sethdford/flowx

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,801 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02801
Opus 5 $0.00000 $0.01401
Sonnet 5 $0.00000 $0.00560
Haiku 4.5 $0.00000 $0.00280

Measured yesterday against content hash 0fa843eb290e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-context-optimization 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.

.cursor/rules/memory-context-optimization.mdc · 443 lines

How it starts

The opening of the file, as written. The whole thing — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Management & Context Optimization Rules

🧠 CONTEXT WINDOW EFFICIENCY

Token Usage Optimization

  • Minimize redundant information - never repeat what's already established
  • Use precise technical language - avoid verbose explanations
  • Reference existing patterns instead of re-explaining them
  • Batch related operations to reduce context switching overhead
  • Prioritize actionable information over background context

AI Interaction Patterns

// ✅ REQUIRED - Efficient AI collaboration
// Be specific: "Fix the memory leak in UserCache.ts line 45"
// Not: "There might be some issues with memory management"

// ✅ REQUIRED - Structured requests
// 1. State the exact problem
// 2. Show the relevant code snippet  
// 3. Specify the desired outcome
// 4. Request tests if needed

// ✅ REQUIRED - Context-aware prompting
// "In the authentication module, add rate limiting to prevent brute force attacks"
// Include: module context + specific action + security reasoning

Chat Organization (Vibe Coding Pattern)

  • Open new chats for distinct tasks to maintain clarity
  • Keep agent chats short and focused (max 10 exchanges)
  • Label chats clearly with purpose ("Feature X", "Bug Fix Y")
  • Reference previous chats when building on past work
  • Document effective prompts for reuse

Memory-Conscious Development

// ✅ REQUIRED - Bounded data structures
class ConversationHistory {
  private readonly maxEntries = 100;
  private entries: ConversationEntry[] = [];
  
  addEntry(entry: ConversationEntry): void {
    this.entries.push(entry);
    if (this.entries.length > this.maxEntries) {
      this.entries.shift(); // Remove oldest
    }
  }
  
  // Use computed properties instead of storing derived data
  get recentEntries(): ConversationEntry[] {
    return this.entries.slice(-10);
  }
}

// ❌ FORBIDDEN - Unbounded growth
class BadHistory {
  private entries: ConversationEntry[] = []; // Grows forever
  private cache = new Map(); // No cleanup strategy
  private allUserActions: UserAction[] = []; // Memory leak
}

Read the full file on GitHub · 443 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 · 443 lines · 0 tokens per session scan A 0fa843eb290e

Subscribe to this mod's changes

memory-context-optimization is a cursor rule published in the GitHub repository sethdford/flowx (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,801 tokens. 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.