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/github/awesome-copilot/agents-mdgit clone --depth 1 https://github.com/github/awesome-copilotWhat 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 | $0.04119 | $0.04119 |
| Opus 5 | $0.02060 | $0.02060 |
| Sonnet 5 | $0.00824 | $0.00824 |
| Haiku 4.5 | $0.00412 | $0.00412 |
Grade A, and why
awesome-copilot 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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- awesome-copilot AGENTS.md — 88% identical, 66 lines differ
How it starts
The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
The Awesome GitHub Copilot repository is a community-driven collection of custom agents and instructions designed to enhance GitHub Copilot experiences across various domains, languages, and use cases. The project includes:
- Agents - Specialized GitHub Copilot agents that integrate with MCP servers
- Instructions - Coding standards and best practices applied to specific file patterns
- Skills - Self-contained folders with instructions and bundled resources for specialized tasks
- Hooks - Automated workflows triggered by specific events during development
- Workflows - Agentic Workflows for AI-powered repository automation in GitHub Actions
- Plugins - Installable packages that group related agents, hooks, and skills around specific themes
Repository Structure
.
├── agents/ # Custom GitHub Copilot agent definitions (.agent.md files)
├── instructions/ # Coding standards and guidelines (.instructions.md files)
├── skills/ # Agent Skills folders (each with SKILL.md and optional bundled assets)
├── hooks/ # Automated workflow hooks (folders with README.md + hooks.json)
├── workflows/ # Agentic Workflows (.md files for GitHub Actions automation)
├── plugins/ # Installable plugin packages (folders with plugin.json)
├── extensions/ # Reusable canvas extension sources (extension.mjs and assets)
├── docs/ # Documentation for different resource types
├── eng/ # Build and automation scripts
└── scripts/ # Utility scripts
Setup Commands
# Install dependencies
npm ci
# Build the project (generates README.md and marketplace.json)
npm run build
# Validate plugin manifests
npm run plugin:validate
# Generate marketplace.json only
npm run plugin:generate-marketplace
# Create a new plugin
npm run plugin:create -- --name <plugin-name>
# Validate agent skills
npm run skill:validate
# Create a new skill
npm run skill:create -- --name <skill-name>
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.
- 2d ago First seen · 354 lines · 4,119 tokens per session scan A a9d9cba52874
awesome-copilot AGENTS.md is an instructions file published in the GitHub repository github/awesome-copilot (38,502 stars, last pushed today), licensed MIT. It adds 4,119 tokens to every session, about $0.0206 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 2026-08-30.
Other instructions, from other repositories
awesome-copilot-studio-agents AGENTS.md
AGENTS.md instructions for kesslernity/awesome-copilot-studio-agents, covering awesome copilot studio agents, ai at work newsletter, free ai course, deploying copilot for your org? and the craft behind these agents.
agenticana copilot-instructions.md
Instructions for ashrafmusa/agenticana, covering agenticana v6.0 — github copilot instructions 🦅, who you are, available agents (use the best one for the task), mcp tools available (use these via copilot chat tools) and agenticana v6.0 power commands.
awesome-agents-md AGENTS.md
AGENTS.md instructions for khasky/awesome-agents-md, covering agents.md, scope and precedence, boundaries, security and verification.
andy-universal-agent-rules AGENTS.md
Instructions for andiupn/andy-universal-agent-rules, covering agents.md, 📋 project overview, 🛠️ tech stack & environment, ⚡ quick commands and knowledge management (core features).
andy-universal-agent-rules copilot-instructions.md
Instructions for andiupn/andy-universal-agent-rules, covering github copilot instructions, quick reference, required reading, critical gotchas and safety rules.
awesome-gemini-cli-subagents GEMINI.md
Gemini CLI instructions for JosephHampton/awesome-gemini-cli-subagents, covering repository context for gemini cli, structure and conventions when editing here.