ai-code-graph

ai-code-graph is a cursor rule for Cursor from sakrut/ai-code-graph. It costs 213 tokens per session, scanned A, original, MIT.

AI Code Graph MCP workflow for C# analysis and edits.

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/sakrut/ai-code-graph/ai-code-graph
Clone the repo
git clone --depth 1 https://github.com/sakrut/ai-code-graph

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai-code-graph

README.md
[![agentmods](https://agentmods.dev/badge/rules/sakrut/ai-code-graph/ai-code-graph.svg)](https://agentmods.dev/rules/sakrut/ai-code-graph/ai-code-graph)
Your own site
<a href="https://agentmods.dev/rules/sakrut/ai-code-graph/ai-code-graph"><img src="https://agentmods.dev/badge/rules/sakrut/ai-code-graph/ai-code-graph.svg" alt="Measured on agentmods" height="20"></a>
Per session 213 This file is loaded in full into every session.
When invoked 213 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00213 $0.00213
Opus 5 $0.00106 $0.00106
Sonnet 5 $0.00043 $0.00043
Haiku 4.5 $0.00021 $0.00021

Measured today against content hash cb76c8f5a2a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-code-graph 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 today.

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.

.cursor/rules/ai-code-graph.mdc · 26 lines

What it actually says

AI Code Graph Integration

If cg_* MCP tools are available, use them for code-understanding tasks.

Before editing any method, call cg_get_context first (when graph data exists) to review complexity, callers, callees, duplicates, and cluster context.

Primary tools:

  • cg_get_context
  • cg_get_hotspots
  • cg_get_callgraph
  • cg_get_impact
  • cg_query
  • cg_dead_code

Secondary tools:

  • cg_token_search, cg_semantic_search, cg_get_similar
  • cg_get_duplicates, cg_get_clusters, cg_export_graph
  • cg_churn, cg_coupling, cg_diff, cg_get_drift, cg_get_tree, cg_analyze

If the database is missing, run cg_analyze first to build ./ai-code-graph/graph.db.

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. today First seen · 26 lines · 213 tokens per session scan A cb76c8f5a2a5

Subscribe to this mod's changes

ai-code-graph is a cursor rule published in the GitHub repository sakrut/ai-code-graph (3 stars, last pushed 5mo ago), licensed MIT. It adds 213 tokens to every session, about $0.0011 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 2026-09-03.