cursor-codeatlas

Rules that connect Cursor to CodeAtlas, a codebase-analysis service that maps project structure, dependencies, and relationships between code elements.

In plain words
What is it for?
Use it to trace features, find functions and classes, inspect dependencies, generate architecture or call-flow diagrams, explore files, and sync the codebase memory after changes.
Why use it?
They help an agent understand related code before editing and keep its stored view of the project current afterward.

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/giauphan/codeatlas-platform/cursor-codeatlas
Clone the repo
git clone --depth 1 https://github.com/giauphan/codeatlas-platform
Per session 634 This file is loaded in full into every session.
When invoked 634 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 $0.00634 $0.00634
Opus 5 $0.00317 $0.00317
Sonnet 5 $0.00127 $0.00127
Haiku 4.5 $0.00063 $0.00063

Measured 2d ago against content hash b4408c7ee560, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-codeatlas 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.

docs/rules-template/cursor-codeatlas.mdc · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeAtlas MCP — Codebase Intelligence

An MCP server named codeatlas is available. It provides code analysis data including project structure, dependencies, and code insights.

Always use CodeAtlas MCP tools BEFORE manual file searches — faster and gives relationship context.

Setup (if not configured)

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "codeatlas": {
      "command": "npx",
      "args": ["-y", "-p", "codeatlas-ai", "codeatlas-mcp"]
    }
  }
}

Workflow

  1. Before making changes → call trace_feature_flow with a keyword to find related files
  2. Looking for a function/class → call search_entities. NEVER use grep or find commands.
  3. Understanding connections → call get_dependencies for import/call relationships
  4. High-level overview → call generate_system_flow for Mermaid architecture diagram
  5. Execution flow of a feature → call generate_feature_flow_diagram for call-chain Mermaid diagram
  6. Exploring a file → call get_file_entities to see all entities in that file
  7. After making changes → call sync_system_memory to update AI memory

Available Tools

Tool When to use
list_projects List all analyzed projects
get_project_structure Overview of modules, classes, functions
get_dependencies Import/call/containment relationships
get_insights AI-generated code quality analysis
search_entities Find function, class, or module by name
get_file_entities All entities inside a specific file
generate_system_flow Mermaid diagram of system architecture (module imports)
generate_feature_flow_diagram Mermaid diagram of feature execution flow (call chains)
sync_system_memory Update .agents/memory/ after code changes
trace_feature_flow Trace feature flow before working on it

Memory & Telemetry Sync

After completing code changes, ALWAYS call the sync_system_memory tool to push details to the remote server and SQLite + sqlite-vec database:

  • changeDescription (ALWAYS required): Description of the changes made
  • businessRule (Optional): Extract and save any new business logic rules mentioned by the user

Read the full file on GitHub · 70 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 · 70 lines · 634 tokens per session scan A b4408c7ee560

Subscribe to this mod's changes

cursor-codeatlas is a cursor rule published in the GitHub repository giauphan/codeatlas-platform (11 stars, last pushed 2d ago), licensed MIT. It adds 634 tokens to every session, about $0.0032 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 2026-08-30.