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.
npx agentmods add instructions/handys11/projgraph/claude-mdgit clone --depth 1 https://github.com/HandyS11/ProjGraphWrote 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.
[](https://agentmods.dev/instructions/handys11/projgraph/claude-md)<a href="https://agentmods.dev/instructions/handys11/projgraph/claude-md"><img src="https://agentmods.dev/badge/instructions/handys11/projgraph/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01067 | $0.01067 |
| Opus 5 | $0.00534 | $0.00534 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
ProjGraph 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
# Restore dependencies
dotnet restore ProjGraph.slnx
# Build
dotnet build ProjGraph.slnx
# Run all tests
dotnet test ProjGraph.slnx
# Run a specific test project
dotnet test tests/ProjGraph.Tests.Unit.ClassDiagram
# Run a specific test class
dotnet test tests/ProjGraph.Tests.Unit.ClassDiagram --filter "ClassAnalysisDepthTests"
# Run CLI locally
dotnet run --project src/ProjGraph.Cli -- visualize ./ProjGraph.slnx
dotnet run --project src/ProjGraph.Cli -- stats ./ProjGraph.slnx
# Run MCP server locally
dotnet run --project src/ProjGraph.Mcp
Build enforces TreatWarningsAsErrors=true and EnforceCodeStyleInBuild=true. XML documentation is required on all public APIs.
Architecture
ProjGraph is a .NET 10 tool ecosystem with two entry points — a CLI (Spectre.Console.Cli) and an MCP server (ModelContextProtocol.Server over stdio) — both backed by a shared library layer.
Dependency graph
Cli ──┐
├──► Lib ──► Lib.Core ──► Core
Mcp ──┘ ├──► Lib.Dependencies ──► Lib.Core
├──► Lib.ClassDiagram ──► Lib.Core
└──► Lib.EntityFramework ──► Lib.Core
ProjGraph.Core— Pure domain models (SolutionGraph,ClassModel,EfModel,SolutionStats) and exceptions. No dependencies.ProjGraph.Lib.Core— Cross-cutting abstractions (IFileSystem,IOutputConsole,ICompilationFactory,IDiagramRenderer<T>), solution parsers (.sln/.slnx), and infrastructure utilities. Also hosts theTarjanSccAlgorithm(inDomain/Algorithms/) used for cycle detection.ProjGraph.Lib.Dependencies— Builds dependency graphs from solution/project files by parsing them directly viaMicrosoft.Build.Construction(the in-houseSlnParser/SlnxParser/ProjectParserinLib.Core); computes stats usingTarjanSccAlgorithmfor cycle detection.ProjGraph.Lib.ClassDiagram— Roslyn-based C# class hierarchy analysis. Accepts a file or directory; optionally discovers related types across the workspace viaIWorkspaceTypeDiscovery.ProjGraph.Lib.EntityFramework— Roslyn semantic analysis of EF CoreDbContextfiles andModelSnapshotfiles; includes a multi-class Fluent API parser.ProjGraph.Lib— Composition root only. ExposesAddProjGraphLib()which wires all sub-library services via DI.
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.
- 3d ago First seen · 91 lines · 1,067 tokens per session scan A a218dd059a4a
ProjGraph CLAUDE.md is an instructions file published in the GitHub repository HandyS11/ProjGraph (1 stars, last pushed 9d ago), licensed MIT. It adds 1,067 tokens to every session, about $0.0053 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.
Other instructions, from other repositories
graphiti AGENTS.md
Instructions for getzep/graphiti, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
code-graph AGENTS.md
AGENTS.md instructions for FalkorDB/code-graph, covering codegraph - agent instructions, architecture, data flow, directory structure and commands.
gemtracker CLAUDE.md
Instructions for spaquet/gemtracker, covering gemtracker development guide, project overview, purpose & vision, technology stack and architecture.
hash rust-review.instructions.md
Review guidance for Rust changes.
graphify-dotnet copilot-instructions.md
Instructions for elbruno/graphify-dotnet, covering graphify-dotnet repository conventions, repository structure, ⚠️ critical rule: all code lives under src/, solution format and project conventions.
hash typescript-review.instructions.md
Review guidance for TypeScript/JavaScript changes.