agentmods.dev

mcp-llm-generator: Instructions file for GitHub Copilot

.github/copilot-instructions.md

mcp-llm-generator copilot-instructions.md is an instructions file for GitHub Copilot from mako10k/mcp-llm-generator. It costs 386 tokens per session, scanned A, original, MIT.

Project instructions for mcp-llm-generator, including how an AI coding assistant should work, which tools and checks to use, and how the server is run in production.

In plain words
What is it for?
Use them when developing or debugging the project, running checks, using its MCP tools, preparing a production build, or managing the server through VS Code Server.
Why use it?
They provide consistent rules for typing, error handling, code reuse, testing, formatting, building, and restarting the server.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is mako10k/mcp-llm-generator's own configuration. It tells GitHub Copilot how to work on mcp-llm-generator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-llm-generator configures →

not rated 2repo 1y ago A scan 386 tokens original MIT
View source ↗ mako10k/mcp-llm-generator
Reuse

Borrowing it

Nothing to install: this file belongs to mako10k/mcp-llm-generator. 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/mako10k/mcp-llm-generator/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/mako10k/mcp-llm-generator

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.

agentmods badge for mcp-llm-generator copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mako10k/mcp-llm-generator/copilot-instructions/github.svg)](https://agentmods.dev/instructions/mako10k/mcp-llm-generator/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/mako10k/mcp-llm-generator/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/mako10k/mcp-llm-generator/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.

agentmods 80×15 button for mcp-llm-generator copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mako10k/mcp-llm-generator/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/mako10k/mcp-llm-generator/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 386 This file is loaded in full into every session.
When invoked 386 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00386 $0.00386
Opus 5.5 $0.00154 $0.00154
Sonnet 5.5 $0.00077 $0.00077
Haiku 4.5 $0.00039 $0.00039

Measured 2mo ago against content hash 5ad31f4a75d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-llm-generator 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 · 44 lines

What it actually says

Copilot Instructions (LLM Friendly)

Role

  • You are GitHub Copilot Assistant.

Responsibilities

  • Help with software development tasks.
  • Suggest code and assist with debugging.

Usage

  • Only use instructions within this document.
  • Use the MCP Association memory Tool for user instructions.
  • Use Google search for the latest information.

Execution

  • Use the MCP Shell tool for commands (do not use run_in_terminal).
  • Do not include explanations in #shell_execute.
  • Ask the user before ignoring or handling errors.
  • Always use strict static type checking.
  • Use type guards to stop if types are incorrect.
  • Ask MCP Context Chat for more details if needed.
  • Never use as unknown as Type for casting.
  • Avoid duplicate code. Use functions or classes for reusable logic.
  • Type check, lint, and format code before suggesting.
  • For production, always build using npm run build:production.
  • In production, VSCode Server manages the MCP Server.
  • Do not invoke MCP Server directly yourself in production.
  • If you stop the MCP Server, restart it using VSCode Server.
  • To restart the MCP Server, use #shell_execute to terminate its process.

Error Handling

  • If a file has syntax or structure errors, notify the user and ask for recovery or clarification.
  • Do not auto-repair or rewrite large broken files unless the user requests it.

Type Safety

  • Always use static type checking first.
  • If not possible, use runtime type guards and throw errors if types are wrong.
  • Never use any, unknown, or cast via unknown.
  • Use runtime type guards only for external SDKs, libraries, or user/external input.

Source Code Language

  • Use English (en) for all code comments, documentation, and literal strings.
  • Translate any non-English comments or strings to English.
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.

  1. 2mo ago First seen · 44 lines · 386 tokens per session scan A 5ad31f4a75d1

Subscribe to this mod's changes

mcp-llm-generator copilot-instructions.md is an instructions file published in the GitHub repository mako10k/mcp-llm-generator (2 stars, last pushed 1y ago), licensed MIT. It adds 386 tokens to every session, about $0.0015 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.

LLMaimcpmodel-context-protocolsamplingtemplates
Related

mcp-llm-generator copilot-instructions.md compared with instructions from other repositories

mcp-llm-generator copilot-instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-llm-generator copilot-instructions.mdmako10k/mcp-llm-generatorInstructions file21y agoMITA386GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode