rules-cursor

Project rules for a codegraph knowledge graph stored in Neo4j, a database designed for connected data. They define commands for querying the graph, checking architecture, and updating it after structural changes.

In plain words
What is it for?
Answering architecture questions, checking conformance, exploring cross-module dependencies with Cypher queries, and reindexing the graph after structural code changes.
Why use it?
They help keep architecture answers and dependency checks based on the project's recorded relationships instead of only searching files.

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/cognitx-leyton/codegraph/rules-cursor
Clone the repo
git clone --depth 1 https://github.com/cognitx-leyton/codegraph
Per session 123 This file is loaded in full into every session.
When invoked 123 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 $0.00123 $0.00123
Opus 5 $0.00062 $0.00062
Sonnet 5 $0.00025 $0.00025
Haiku 4.5 $0.00012 $0.00012

Measured 2d ago against content hash 124449ebc9c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rules-cursor 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.

codegraph/codegraph/templates/platforms/rules-cursor.mdc · 13 lines

What it actually says

This project has a codegraph knowledge graph in Neo4j (bolt://localhost:$NEO4J_BOLT_PORT).

Rules:

  • Before answering architecture or codebase questions, run codegraph query "MATCH ..." or read codegraph-out/GRAPH_REPORT.md
  • Use codegraph arch-check to verify architecture conformance
  • After structural code changes, run codegraph index . --since HEAD~1 to update the graph
  • For cross-module dependency questions, prefer Cypher queries over grep
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 · 13 lines · 123 tokens per session scan A 124449ebc9c3

Subscribe to this mod's changes

rules-cursor is a cursor rule published in the GitHub repository cognitx-leyton/codegraph (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 123 tokens to every session, about $0.0006 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.