40-context-memory

A task-starting rule for reading a project's profile, canonical rules, and memory files before working. These files record repository facts, decisions, and lessons.

In plain words
What is it for?
Use it when starting or resuming tasks and after major changes that require updating project decisions or lessons.
Why use it?
It reduces work based on stale context or rules that conflict with the project's own instructions.

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/luxvil/ai-coding-rules/40-context-memory
Clone the repo
git clone --depth 1 https://github.com/Luxvil/ai-coding-rules

Made for: Cursor.

Per session 90 This file is loaded in full into every session.
When invoked 90 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 $0.00090 $0.00090
Opus 5 $0.00045 $0.00045
Sonnet 5 $0.00018 $0.00018
Haiku 4.5 $0.00009 $0.00009

Measured yesterday against content hash 1cd0a9fad929, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

40-context-memory 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 40-context-memory — 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/40-context-memory.mdc · 17 lines

What it actually says

Context & Memory

Read First

  • project_profile.md (repo truths)
  • MASTER_RULES.md (canonical rules)

Memory Bank

  • Use MEMORY_BANK.md and AGENTS.md as single source of truth.
  • After major changes, update decisions and lessons learned.
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 · 17 lines · 90 tokens per session scan A 1cd0a9fad929

Subscribe to this mod's changes

40-context-memory is a cursor rule published in the GitHub repository Luxvil/ai-coding-rules (3 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to 40-context-memory, differing in 0 lines, and is treated as a copy.