What is agent-plugins copilot-instructions.md?

A repository instruction file for an agent-skills catalogue that collects skills from many provider repositories and publishes generated JSON catalogues.

Use it when maintaining provider definitions, parsing skill files, generating catalogue outputs, or checking the automated daily aggregation.

It explains how the catalogue is aggregated, versioned, and consumed, so changes fit the existing update workflow.

agent-plugins copilot-instructions.md — Instructions file by dmgrok

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/dmgrok/agent-plugins/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/dmgrok/agent-plugins

Made for: GitHub Copilot.

Per session 3,656 This file is loaded in full into every session.

When invoked 3,656 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.03656	$0.03656
Opus 5	$0.01828	$0.01828
Sonnet 5	$0.00731	$0.00731
Haiku 4.5	$0.00366	$0.00366

Measured 2d ago against content hash 464046020675, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-plugins copilot-instructions.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.

.github/copilot-instructions.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Skills Directory - AI Agent Instructions

Project Overview

This repository aggregates agent skills from 41 provider repositories (Anthropic, OpenAI, GitHub, Vercel, HuggingFace, Stripe, Cloudflare, Supabase, and 33+ community repos) into a unified JSON catalog consumed by MCP servers and AI agents. A GitHub Action runs daily at 06:00 UTC to fetch the latest skills, generating versioned releases with YYYY.MM.DD format.

Current stats: 250+ skills, 41 providers, 150K+ combined GitHub stars

Key consumers: MCP Mother Skills server.

Architecture

Core Components

scripts/aggregate.py - Main aggregation script (425 lines)
- Fetches skills from GitHub API using tree endpoints
- Parses SKILL.md files with YAML frontmatter
- Generates 2 output formats: catalog.json, catalog.min.json
- Auto-updates CHANGELOG.md with version metadata
- Uses GITHUB_TOKEN env var to avoid rate limits
Provider System - Extensible provider configuration (lines 35-207 in aggregate.py)
```
PROVIDERS = {
    "provider-id": {
        "name": "Display Name",
        "repo": "https://github.com/org/repo",
        "api_tree_url": "https://api.github.com/repos/.../git/trees/main?recursive=1",
        "raw_base": "https://raw.githubusercontent.com/.../main",
        "skills_path_prefix": "skills/",  # Can be "" for root-level SKILL.md
    }
}
```
- Add new providers by extending this dict - no other code changes needed
- Supports root-level SKILL.md files (single-skill repos) with skills_path_prefix: ""
- Some repos use master branch instead of main - adjust URLs accordingly
- Provider stats include stars and description fetched from GitHub API
Category System - Keyword-based auto-categorization (lines 67-74)
- Maps skills to categories: documents, development, creative, enterprise, integrations, data, security, cloud, mobile, ml-ai, testing, devops, web, other
- Based on keyword matching in name/description
- To add categories: extend CATEGORY_KEYWORDS dict

Read the full file on GitHub · 296 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.

2d ago First seen · 296 lines · 3,656 tokens per session scan A 464046020675

Subscribe to this mod's changes

agent-plugins copilot-instructions.md is an instructions file published in the GitHub repository dmgrok/agent-plugins (18 stars, last pushed 2d ago), licensed MIT. It adds 3,656 tokens to every session, about $0.0183 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.

Planning agent mcp-server skills

agent-plugins copilot-instructions.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Agent Skills Directory - AI Agent Instructions

Project Overview

Architecture

Core Components

What this file has done since we first saw it

Other instructions, from other repositories

webflow-skills CLAUDE.md

MathModelAgent CLAUDE.md

rolecraft AGENTS.md

lime AGENTS.md

clean-code-skills clean-code.instructions.md

wtcraft CLAUDE.md