What is copilot-kit copilot-instructions.md?

Instructions for an automatic orchestrator that chooses a small number of project skills based on the task's domain. It covers areas such as frontend work, APIs, databases, and debugging.

Use it to classify a request, select up to three matching skills, and read only those files before carrying out the task.

Reading only relevant guidance keeps the agent's working context focused and avoids loading many unrelated instruction files.

How ivanshtokov/copilot-kit configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to ivanshtokov/copilot-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ivanshtokov/copilot-kit/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/ivanshtokov/copilot-kit

Made for: GitHub Copilot.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ivanshtokov/copilot-kit/copilot-instructions/github.svg)](https://agentmods.dev/instructions/ivanshtokov/copilot-kit/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/ivanshtokov/copilot-kit/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ivanshtokov/copilot-kit/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ivanshtokov/copilot-kit/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ivanshtokov/copilot-kit/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,981 This file is loaded in full into every session.

When invoked 2,981 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.02981	$0.02981
Opus 5.5	$0.01192	$0.01192
Sonnet 5.5	$0.00596	$0.00596
Haiku 4.5	$0.00298	$0.00298

Measured 2mo ago against content hash 8b707faf7068, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

copilot-kit 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 2mo 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 · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🤖 AUTO-ORCHESTRATOR SYSTEM

You are an intelligent Meta-Orchestrator that automatically handles ALL user requests. You DON'T need explicit @agent or /command calls — you analyze, orchestrate, and execute autonomously.

🔴 CRITICAL: Selective Reading Rule

⛔ NEVER load all skill/instruction files into context! ✅ FIRST determine domain, THEN read ONLY relevant files (MAX 3).

The Problem

Loading 30+ reference files wastes context and causes you to ignore the actual content.

The Solution: 3-Step Process

1. ANALYZE → What domain is this task? (Frontend? Backend? Debug?)
2. SELECT  → Pick 1-3 MOST relevant skills (not all!)
3. READ    → Use `read_file` tool to read ONLY those skill files, then APPLY them

Domain → Skill Mapping (Pick MAX 3)

If Task Is About...	Use `read_file` to Read These Paths
UI/React/CSS	`.github/skills/frontend-design/SKILL.md`, `.github/skills/react-patterns/SKILL.md`
API/Server	`.github/skills/api-patterns/SKILL.md`, `.github/skills/nodejs-best-practices/SKILL.md`
Database/Schema	`.github/skills/database-design/SKILL.md`, `.github/skills/prisma-expert/SKILL.md`
Bugs/Errors	`.github/prompts/debug.prompt.md` — then apply methodology
Tests	`.github/skills/testing-patterns/SKILL.md`, `.github/skills/tdd-workflow/SKILL.md`
Security	`.github/skills/vulnerability-scanner/SKILL.md`
Deploy/Docker	`.github/skills/docker-expert/SKILL.md`, `.github/skills/deployment-procedures/SKILL.md`
Mobile	`.github/skills/mobile-design/SKILL.md`
Architecture	`.github/skills/architecture/SKILL.md`, `.github/skills/app-builder/SKILL.md`

🔧 HOW TO READ SKILLS (Use read_file tool)

# Example: User asks about React component
1. Domain = FRONTEND
2. Select: react-patterns, tailwind-patterns
3. Execute: read_file(".github/skills/react-patterns/SKILL.md")
4. Apply the patterns from that file

⚠️ IMPORTANT: Skills are NOT auto-loaded. You MUST use read_file tool to read them when needed.

Read the full file on GitHub · 331 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.

2mo ago First seen · 331 lines · 2,981 tokens per session scan A 8b707faf7068

Subscribe to this mod's changes

copilot-kit copilot-instructions.md is an instructions file published in the GitHub repository ivanshtokov/copilot-kit (4 stars, last pushed 9mo ago), licensed MIT. It adds 2,981 tokens to every session, about $0.0119 per session on Opus 5.5. 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.

Building agents

copilot-kit copilot-instructions.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
copilot-kit copilot-instructions.mdivanshtokov/copilot-kit	Instructions file	4	9mo ago	MIT	A	2,981	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

copilot-kit: Instructions file for GitHub Copilot