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/ivanshtokov/copilot-kit/copilot-instructionsgit clone --depth 1 https://github.com/ivanshtokov/copilot-kitWhat 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 | $0.02981 | $0.02981 |
| Opus 5 | $0.01491 | $0.01491 |
| Sonnet 5 | $0.00596 | $0.00596 |
| Haiku 4.5 | $0.00298 | $0.00298 |
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 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.
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.
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 · 331 lines · 2,981 tokens per session scan A 8b707faf7068
copilot-kit copilot-instructions.md is an instructions file published in the GitHub repository ivanshtokov/copilot-kit (2 stars, last pushed 7mo ago), licensed MIT. It adds 2,981 tokens to every session, about $0.0149 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.