ruleProb copilot-instructions.md

ruleProb copilot-instructions.md is an instructions file for GitHub Copilot from canblmz1/ruleProb. It costs 19 tokens per session, scanned A, original, MIT.

Project rules for checking whether instructions given to AI coding agents are actually followed during execution. They include rules such as not editing generated source files and not running destructive shell commands.

In plain words
What is it for?
Use it to test instruction files such as CLAUDE.md, AGENTS.md, and Cursor rules in sandbox scenarios. It extracts the rules, runs checks, and scores compliance.
Why use it?
It helps reveal when an AI agent ignores or breaks project instructions. This reduces the need to trust that written rules are being followed without testing them.

Instructions file for GitHub Copilot

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/canblmz1/ruleprob/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/canblmz1/ruleProb

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 ruleProb copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/canblmz1/ruleprob/copilot-instructions.svg)](https://agentmods.dev/instructions/canblmz1/ruleprob/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/canblmz1/ruleprob/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/canblmz1/ruleprob/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 This file is loaded in full into every session.
When invoked 19 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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00019
Opus 5 $0.00010 $0.00010
Sonnet 5 $0.00004 $0.00004
Haiku 4.5 $0.00002 $0.00002

Measured 3d ago against content hash f4a2598eae30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ruleProb 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 3d 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.

examples/basic/.github/copilot-instructions.md · 5 lines

What it actually says

Copilot Instructions

  • Never edit src/generated/*
  • Do not run destructive shell commands.
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. 3d ago First seen · 5 lines · 19 tokens per session scan A f4a2598eae30

Subscribe to this mod's changes

ruleProb copilot-instructions.md is an instructions file published in the GitHub repository canblmz1/ruleProb (7 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session, about $0.0001 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.