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/peterblazejewicz/claude-plugins/agents-mdgit clone --depth 1 https://github.com/peterblazejewicz/claude-pluginsWrote 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/peterblazejewicz/claude-plugins/agents-md)<a href="https://agentmods.dev/instructions/peterblazejewicz/claude-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/peterblazejewicz/claude-plugins/agents-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 | $0.00934 | $0.00934 |
| Opus 5 | $0.00467 | $0.00467 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
claude-plugins AGENTS.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 4d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions (cross-vendor)
This repository is a plugin marketplace consumed by both Claude Code and GitHub Copilot CLI. The full contributor guide lives in CLAUDE.md — read it first.
What this repo publishes
Two plugins, declared in .claude-plugin/marketplace.json:
- avalonia-dev — Avalonia / MAUI structural review (project layout, design tokens, theming, phased migration) for Avalonia 11.x and 12.x.
- dotnet-skills — 21 agent skills + 3 specialized subagents for .NET 8+ engineering (spec → plan → build → verify → review → ship). Indirect fork of addyosmani/agent-skills (MIT © 2025 Addy Osmani).
Both plugins install via claude plugins install <name> (Claude Code) or copilot plugin marketplace add <owner>/<repo> + /plugin install <name> (Copilot CLI). Copilot CLI reads .claude-plugin/marketplace.json directly — the path is deliberate cross-tool compatibility.
Two load-bearing invariants when changing dotnet-skills
A contributor can't learn these from the code alone — they're captured lessons from prior regressions.
- Version coupling. Any user-visible change to
plugins/dotnet-skills/requires bumping bothplugins/dotnet-skills/.claude-plugin/plugin.jsonand the matching entry in.claude-plugin/marketplace.json. The plugin cache is version-keyed —claude plugins marketplace updatewon't refetch an already-cached version, so same-version republishes are invisible. - Test-sample policy. Native
Xunit.Assert.X(xUnit) orMicrosoft.VisualStudio.TestTools.UnitTesting.Assert.X(MSTest) only. Do not introduce FluentAssertions in new samples or prose — v8+ (January 2025) moved to the XCEED source-available license. xUnit v3 + Microsoft.Testing.Platform is canonical; v2 stays source-compatible for Avalonia 11.x (which only gained xUnit v3 headless support in Avalonia 12.0, April 2026).
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.
- 4d ago First seen · 34 lines · 934 tokens per session scan A 22245cac0faa
claude-plugins AGENTS.md is an instructions file published in the GitHub repository peterblazejewicz/claude-plugins (7 stars, last pushed 2mo ago), licensed MIT. It adds 934 tokens to every session, about $0.0047 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
ai-ready AGENTS.md
Instructions for johnpapa/ai-ready, covering ai-ready repo — agent guide, repository structure, tech stack, build & run and testing.
ai-ready copilot-instructions.md
Instructions for johnpapa/ai-ready, covering copilot instructions — ai-ready, project type, writing conventions, markdown and yaml (skill frontmatter, workflows, issue templates).
ownership-driven-ai-customization-architecture copilot-instructions.md
Instructions for HenriqueCotta/ownership-driven-ai-customization-architecture: This repository documents and distributes the Ownership-Driven Architecture.
my-awesome-copilot agent-skills.instructions.md
Guidelines for creating high-quality Agent Skills for GitHub Copilot.
my-awesome-copilot prompt.instructions.md
Guidelines for creating high-quality prompt files for GitHub Copilot.
my-awesome-copilot AGENTS.md
AGENTS.md instructions for JakeTRogers/my-awesome-copilot, covering my-awesome-copilot, commands, architecture, conventions and gotchas.