cursorrules

A persistent memory system for coding agents that saves knowledge about a codebase between conversations. It can restore prior work, project structure, recent changes, and commonly edited files.

In plain words
What is it for?
Resuming coding tasks, finding files or symbols by name or meaning, searching code, tracing dependencies, and recording session summaries.
Why use it?
It reduces repeated file reading and helps an agent continue work without losing context from an earlier session.

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/shdra06/ai-mind-map/cursorrules
Clone the repo
git clone --depth 1 https://github.com/shdra06/ai-mind-map

Made for: Cursor.

Per session 1,132 This file is loaded in full into every session.
When invoked 1,132 The same file — it is already loaded in full.
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 $0.01132 $0.01132
Opus 5 $0.00566 $0.00566
Sonnet 5 $0.00226 $0.00226
Haiku 4.5 $0.00113 $0.00113

Measured yesterday against content hash c755e0503503, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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.

.cursorrules · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Mind Map MCP — Code Memory Engine (v1.4.0)

You have the AI Mind Map MCP server connected. It is a persistent code memory system that eliminates redundant file re-reading and context loss between sessions.

🚀 FIRST THING TO DO IN EVERY CONVERSATION

Call mindmap_session_resume — it returns:

  • What the previous AI agent worked on
  • What code changed since then (function-level diffs, not just file names)
  • Project structure + tech stack
  • Hot files (most frequently modified)

This ONE call replaces reading 10+ files (~2000 tokens instead of 50,000+).

Quick Lookup: "I need to..." → Use this tool

⚡ Session Lifecycle (always use these)

  • Resume from last session → mindmap_session_resume ⭐⭐ (THE first call)
  • Start tracking a new task → mindmap_session_start
  • End session, save summary → mindmap_session_end

🔍 Find Code (instead of grep/reading files)

  • Search by name → mindmap_smart_search ⭐ (returns full context)
  • Search by concept → mindmap_semantic_search ⭐ ("authentication", "error handling")
  • Grep text in code → mindmap_search_code
  • Who calls X? → mindmap_trace_dependencies
  • All usages of symbol → mindmap_find_references

📖 Read Code (without reading full files)

  • Everything about a symbol → mindmap_explain ⭐ (signature + callers + callees + doc in ONE call)
  • Read actual source code → mindmap_get_code_snippet
  • Understand file without reading → mindmap_file_digest ⭐ (saves 3-10K tokens/file)
  • All symbols in a file → mindmap_get_file_map
  • Just the signature → mindmap_get_signature (cheapest read)

📊 Understand the Project

  • Full project summary → mindmap_digest ⭐ (<2000 tokens)
  • Architecture overview → mindmap_architecture
  • Full project map → mindmap_project_map
  • Layer overview → mindmap_layer_overview

🔄 Change Tracking

  • Symbol-level diffs → mindmap_changelog ⭐ (added/modified/deleted functions)
  • Git-aware changes → mindmap_git_changes (maps diffs to symbols)
  • Check if cached code is valid → mindmap_verify ⭐ (hash check, no re-reading)
  • Most changed files → mindmap_hotspots
  • What changed recently? → mindmap_what_changed
  • Changes since last session → mindmap_session_diff

Read the full file on GitHub · 97 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 · 97 lines · 1,132 tokens per session scan A c755e0503503

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository shdra06/ai-mind-map (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,132 tokens to every session, about $0.0057 per session on Opus 5. 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.