cursor-aidumem

A code-change memory hook that saves substantial changes to aiduMEI's local Raw Drawer, a place for long-term recall.

In plain words
What is it for?
Recording new functions, bug fixes, design decisions, API work, and configuration changes while skipping minor edits.
Why use it?
It preserves useful context about completed work so it can be recalled later instead of being lost after a session.

Cursor rule

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/monkey2jack/aidumei/cursor-aidumem
Clone the repo
git clone --depth 1 https://github.com/monkey2jack/aiduMEI
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 247 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 $0.00247
Opus 5 $0.00000 $0.00123
Sonnet 5 $0.00000 $0.00049
Haiku 4.5 $0.00000 $0.00025

Measured 2d ago against content hash 875fa73cc0b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-aidumem 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.

integrations/cursor-hook/cursor-aidumem.mdc · 39 lines

What it actually says

aiduMEI Code Memory Hook

When you make significant code changes (new functions, refactors, bug fixes), automatically store them to aiduMEI's Raw Drawer for long-term recall.

Trigger

After completing a meaningful code change (not trivial one-liners), call:

POST http://127.0.0.1:8767/add/raw
Content-Type: application/json

{
  "content": "FILE: <relative_path>\n\n<code_snippet_or_summary>",
  "source": "cursor_hook",
  "user_id": "default"
}

What to Store

✅ Store:

  • New functions/classes with their docstrings
  • Bug fix descriptions with before/after
  • Architectural decisions ("moved X to Y because...")
  • API endpoint implementations
  • Configuration changes with rationale

❌ Skip:

  • Trivial whitespace/formatting changes
  • Single-line variable renames
  • Auto-generated code
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 · 39 lines · 0 tokens per session scan A 875fa73cc0b1

Subscribe to this mod's changes

cursor-aidumem is a cursor rule published in the GitHub repository monkey2jack/aiduMEI (18 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 247 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 2026-08-30.