repository-instructions

repository-instructions is a cursor rule for Cursor from franklesniak/copilot-repo-template. It costs 2,521 tokens per session, scanned A, original, MIT.

Project rules and instructions for Cursor Agent and compatible AI coding tools. They point to the repository's main instruction file and summarise the rules agents must follow.

In plain words
What is it for?
Use it when an AI coding agent works in the repository and needs to know which instructions and files are authoritative.
Why use it?
It gives coding agents a consistent source of project standards, safety requirements and workflow guidance.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Cursor.

Good fit Use it when an AI coding agent works in the repository and needs to know which instructions and files are authoritative.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/franklesniak/copilot-repo-template/repository-instructions
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.

Clone the repo
git clone --depth 1 https://github.com/franklesniak/copilot-repo-template

Made for: Cursor.

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 repository-instructions

README.md
[![agentmods](https://agentmods.dev/badge/rules/franklesniak/copilot-repo-template/repository-instructions/github.svg)](https://agentmods.dev/rules/franklesniak/copilot-repo-template/repository-instructions)
Your own site
<a href="https://agentmods.dev/rules/franklesniak/copilot-repo-template/repository-instructions"><img src="https://agentmods.dev/badge/rules/franklesniak/copilot-repo-template/repository-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 repository-instructions

Your own site · 80×15
<a href="https://agentmods.dev/rules/franklesniak/copilot-repo-template/repository-instructions"><img src="https://agentmods.dev/badge/rules/franklesniak/copilot-repo-template/repository-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,521 This file is loaded in full into every session.
When invoked 2,521 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 $0.02521 $0.02521
Opus 5 $0.01260 $0.01260
Sonnet 5 $0.00504 $0.00504
Haiku 4.5 $0.00252 $0.00252

Measured 10d ago against content hash dfe405d4fb99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

repository-instructions 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 10d 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.

.cursor/rules/repository-instructions.mdc · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions for Cursor Agent

Version: 1.1.20260629.0

Metadata

  • Status: Active
  • Owner: Repository Maintainers
  • Last Updated: 2026-06-29
  • Scope: Agent-specific project rule for Cursor Agent and compatible AI coding agents operating in this repository. Mirrors a minimal inline summary of the highest-priority shared rules; .github/copilot-instructions.md remains the canonical source of truth.

This file provides project-specific instructions for Cursor Agent and compatible AI coding agents operating in this repository. These instructions ensure that agents follow the same coding standards, safety rules, and workflows that apply to all contributors.

Canonical Instructions

The authoritative source of truth for all repository rules is .github/copilot-instructions.md (the repo-wide constitution). All rules defined there apply without exception. Read that file before making any changes.

This file intentionally keeps only a minimal inline summary of the highest-priority shared rules so that Cursor receives critical guidance immediately. The full shared rule set remains in the canonical file above.

Thin entry point classification: A thin entry point keeps shared repository rules brief; it does not mean platform-specific or required protocol sections may be discarded. Sections explicitly labeled as platform protocol or required protocol must be preserved unless the repository owner explicitly waives that protocol for the retained agent platform.

Protected Instruction Files

Instruction files and style guides are protected governance files. Do not create, edit, delete, rename, or otherwise change .github/copilot-instructions.md, files under .github/instructions/, files under .cursor/rules/, or root agent instruction files (.hermes.md, AGENTS.md, CLAUDE.md, GEMINI.md) unless the repository owner or maintainer has directly and explicitly authorized that specific instruction-file change in the current task. Implied consent is not enough; do not infer authorization from a plan you generated, review feedback, a general request to update docs, cleanup/validation work, or a "keep files in sync" instruction.

Read the full file on GitHub · 148 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.

  1. 10d ago First seen · 148 lines · 2,521 tokens per session scan A dfe405d4fb99

Subscribe to this mod's changes

repository-instructions is a cursor rule published in the GitHub repository franklesniak/copilot-repo-template (8 stars, last pushed 24d ago), licensed MIT. It adds 2,521 tokens to every session, about $0.0126 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.