copilot-instructions

Development instructions for the ProjGraph project, including its technologies, architecture, and project-specific implementation rules.

In plain words
What is it for?
Use them when implementing, reviewing, testing, or documenting ProjGraph features such as MCP tools, diagrams, package data, or documentation.
Why use it?
They give coding agents the context needed to follow the project’s established design and tooling.

Agent

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 agents/handys11/projgraph/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/HandyS11/ProjGraph
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 831 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00831
Opus 5 $0.00000 $0.00415
Sonnet 5 $0.00000 $0.00166
Haiku 4.5 $0.00000 $0.00083

Measured 2d ago against content hash b2db7db5580c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot-instructions 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.

.github/agents/copilot-instructions.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ProjGraph Development Guidelines

Auto-generated from all feature plans. Last updated: 2026-01-13

Active Technologies

  • .NET 10.0 (C# 14+) + ModelContextProtocol v1.0.0, Microsoft.Extensions.Hosting (012-mcp-integration-primitives)

  • In-memory only (DiagramResourceCache singleton, max 50 entries, LRU eviction) (012-mcp-integration-primitives)

  • .NET 10.0 (C# 14+) + mcp-publisher (npm), GitHub Actions (011-mcp-registry-submission)

  • .NET 10.0 (C# 14+) + Spectre.Console.Cli (CLI formatting), ModelContextProtocol.Server (MCP tool), System.Text.Json (MCP response serialisation), Microsoft.Extensions.DependencyInjection (DI wiring) ( 010-project-stats-mcp)

  • N/A — pure in-memory computation over SolutionGraph (010-project-stats-mcp)

  • N/A (Memory analysis) (009-directory-class-diagram)

  • .NET 10.0 (C# 14+) + Microsoft.Build.Construction (for project parsing), Spectre.Console (for rendering) ( 008-nuget-package-rendering)

  • N/A (In-memory graph processing) (008-nuget-package-rendering)

  • .NET 10.0 (C# 14+) for API metadata extraction + DocFX (v2.70+), Mermaid.js (v10+), GitHub Actions ( 006-docfx-documentation)

  • N/A (Static site) (006-docfx-documentation)

  • .NET 10.0 (C# 14+) + ProjGraph.Cli (local build), .NET SDK 10.0 (005-improve-samples)

  • Local file system (Markdown, C# Source, .slnx Solution Explorers) (005-improve-samples)

  • .NET 10.0 (C# 14+) + Microsoft.CodeAnalysis.CSharp (Roslyn), ProjGraph.Lib.Core (004-config-class-members)

  • .NET 10.0 (C# 14+) + Microsoft.CodeAnalysis.CSharp, Spectre.Console (003-mermaid-class-diagram)

  • .NET 10.0 (C# 14+) + Microsoft.CodeAnalysis.CSharp, Microsoft.CodeAnalysis.Workspaces.MSBuild, Microsoft.EntityFrameworkCore (for symbol analysis) (002-dbcontext-erd)

  • .NET 10.0 (C# 14+) + Buildalyzer (Parsing), Spectre.Console (CLI), ModelContextProtocol (MCP) (001-cli-graph-rendering)

Project Structure

src/
tests/

Commands

Add commands for .NET 10.0 (C# 14+)

Read the full file on GitHub · 78 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 · 78 lines · 0 tokens per session scan A b2db7db5580c

Subscribe to this mod's changes

copilot-instructions is an agent published in the GitHub repository HandyS11/ProjGraph (1 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 831 tokens. 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.