dotnet-skills AGENTS.md

Repository instructions for dotnet-skills, a catalog of reusable guidance for modern and older .NET software. The file explains the repository structure, how general and folder-specific rules take precedence, and how its catalog, agents, and release automation are maintained.

In plain words
What is it for?
Use it when maintaining catalog entries, repository-owned agents, package agents, or release and documentation monitoring. It is also useful before changing the repository’s layout or build automation.
Why use it?
It gives an AI assistant the project context needed to update the catalog or automation without turning the repository into an unrelated application. It also clarifies where different kinds of files belong.

Instructions file for CodexOpenCode

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 instructions/managedcode/dotnet-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/managedcode/dotnet-skills

Made for: Codex, OpenCode.

Per session 13,592 This file is loaded in full into every session.
When invoked 13,592 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.13592 $0.13592
Opus 5 $0.06796 $0.06796
Sonnet 5 $0.02718 $0.02718
Haiku 4.5 $0.01359 $0.01359

Measured yesterday against content hash 7eac11d9b095, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotnet-skills AGENTS.md scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- It is acceptable to use `curl` for non-GitHub documentation endpoints.
AGENTS.md · 721 lines

How it starts

The opening of the file, as written. The whole thing — 721 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project: dotnet-skills Stack: .NET 10, GitHub Actions, Python automation, NuGet, GitHub Releases

Follows MCAF


Purpose

This file defines how AI agents work in this repository.

  • Root AGENTS.md holds the global workflow, repository structure, release and automation policy, and skill-catalog maintenance rules.
  • This repository currently uses only the root AGENTS.md; add a nearer local AGENTS.md only when a subtree needs stricter or more specialized rules.
  • The repository has three equally important responsibilities:
    1. Maintain a high-quality scanned catalog under catalog/<type>/<package>/ for modern and legacy .NET.
    2. Maintain repo-owned orchestration agents in top-level agents/ and package-owned catalog agents in catalog/<type>/<package>/agents/.
    3. Maintain automation that watches official upstream releases and documentation so the catalog can be refreshed when the ecosystem changes.

If this repository contains executable code, it must exist only to distribute or install the skill catalog itself, for example as a publishable dotnet tool. Do not turn this repository into a general application or unrelated tooling codebase.

All repository-facing documentation and skill content should be written in English. Follow official or documented agent standards where they exist; do not present a repo-local adapter as if it were a universal standard.

Solution Topology

  • Solution root: .
  • Areas with specialized responsibilities:
    • agents/: top-level orchestration agents that sit above the skill catalog, one folder per agent
    • catalog/: canonical scanned catalog tree, including package manifests plus nested skills and package-owned agents
    • external-sources/: vendir transport config, pinned lockfile, checked-in upstream snapshots, and import overrides for external repositories
    • cli/ManagedCode.DotnetAgents/: publishable dotnet-agents installer tool for repo-owned orchestration agents
    • cli/ManagedCode.Agents/: publishable agents installer tool for the same repo-owned orchestration agents
    • cli/ManagedCode.DotnetSkills/: publishable dotnet-skills installer tool
    • scripts/: catalog generation and upstream-watch automation
    • .github/workflows/: CI, release, and scheduled automation
  • Local AGENTS.md files currently present: none

Read the full file on GitHub · 721 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. yesterday First seen · 721 lines · 13,592 tokens per session scan A 7eac11d9b095

Subscribe to this mod's changes

dotnet-skills AGENTS.md is an instructions file published in the GitHub repository managedcode/dotnet-skills (477 stars, last pushed 2d ago), licensed MIT. It adds 13,592 tokens to every session, about $0.0680 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories