agentmods.dev

ai-code-graph: Instructions file for Claude Code

CLAUDE.md

ai-code-graph CLAUDE.md is an instructions file for Claude Code from sakrut/ai-code-graph. It costs 1,154 tokens per session, scanned A, original, MIT.

Project instructions for AI Code Graph, a .NET tool that reads C# code and stores relationships between its parts in a SQLite database.

In plain words
What is it for?
Use it when building, testing, packaging, or configuring AI Code Graph for Claude Code or Cursor.
Why use it?
It gives contributors the commands, project layout, setup helpers, and testing information needed to work on the codebase.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is sakrut/ai-code-graph's own configuration. It tells Claude Code how to work on ai-code-graph itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-code-graph configures →

not rated 3repo 6mo ago A scan 1,154 tokens original MIT
View source ↗ sakrut/ai-code-graph
Reuse

Borrowing it

Nothing to install: this file belongs to sakrut/ai-code-graph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sakrut/ai-code-graph/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sakrut/ai-code-graph

Made for: Claude Code.

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sakrut/ai-code-graph/claude-md/github.svg)](https://agentmods.dev/instructions/sakrut/ai-code-graph/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sakrut/ai-code-graph/claude-md"><img src="https://agentmods.dev/badge/instructions/sakrut/ai-code-graph/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-code-graph CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sakrut/ai-code-graph/claude-md"><img src="https://agentmods.dev/badge/instructions/sakrut/ai-code-graph/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,154 This file is loaded in full into every session.
When invoked 1,154 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01154 $0.01154
Opus 5 $0.00577 $0.00577
Sonnet 5 $0.00231 $0.00231
Haiku 4.5 $0.00115 $0.00115

Measured 5d ago against content hash a5cef04c97df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai-code-graph CLAUDE.md 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 5d 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.

CLAUDE.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions

Project Overview

AI Code Graph is a .NET 8.0 Roslyn-based static analysis tool packaged as a global CLI tool. It analyzes .NET solutions to build semantic code graphs stored in SQLite.

Build & Test

dotnet build                          # Build all projects
dotnet test                           # Run all tests (303 tests)
dotnet test --filter "ClassName"      # Run specific test class
dotnet pack AiCodeGraph.Cli           # Package as global tool

AI Setup Helpers

ai-code-graph setup-claude           # Scaffold Claude slash commands + MCP config
ai-code-graph setup-cursor           # Scaffold Cursor MCP config + rule + project skill

Project Structure

  • AiCodeGraph.Cli/ - CLI entry point using System.CommandLine 2.0.2. All commands defined in Program.cs.
  • AiCodeGraph.Core/ - Core library with all analysis logic. Subdivided by concern:
    • Models/ - CodeGraph models, LoadedWorkspace record
    • CallGraph/ - CallGraphBuilder using Roslyn semantic model
    • Metrics/ - MetricsEngine for cognitive complexity
    • Normalization/ - IntentNormalizer for structural signatures and semantic payloads
    • Embeddings/ - HashEmbeddingEngine (384-dim feature hashing), VectorIndex (SIMD cosine similarity)
    • Duplicates/ - StructuralCloneDetector, SemanticCloneDetector, HybridScorer, IntentClusterer (DBSCAN)
    • Drift/ - DriftDetector comparing two SQLite databases
    • Storage/ - StorageService (SQLite), SchemaDefinition
  • AiCodeGraph.Tests/ - xUnit tests
  • tests/fixtures/TestSolution/ - Multi-project fixture for integration tests

Key Patterns

  • System.CommandLine: Uses SetAction() on commands, Option<T> for parameters. Stable 2.0.2 API.
  • Storage: StorageService wraps Microsoft.Data.Sqlite. Call InitializeAsync() to create tables, or OpenAsync() for existing DBs.
  • Embeddings: Deterministic hash-based (no ML models). HashEmbeddingEngine implements IEmbeddingEngine.
  • Clone Detection: Three-layer approach - structural (Jaccard on tokens), semantic (kNN on vectors), hybrid (weighted merge).
  • MSBuild Locator: Called once in WorkspaceLoader constructor. Integration tests wrap in try-catch for environments without MSBuild.

Read the full file on GitHub · 98 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. 5d ago First seen · 98 lines · 1,154 tokens per session scan A a5cef04c97df

Subscribe to this mod's changes

ai-code-graph CLAUDE.md is an instructions file published in the GitHub repository sakrut/ai-code-graph (3 stars, last pushed 6mo ago), licensed MIT. It adds 1,154 tokens to every session, about $0.0058 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.

Analytics and metricsC# and .NETLanguages
Related

Other instructions, from other repositories

graftcode graftcode-dotnet.instructions.md

Instructions for grft-dev/graftcode, covering graftcode — .net backend services, when this applies (always), authoritative docs (source of truth), golden rules and service = .net class library.

grft-dev/graftcode · 7,060 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens