Vibe-Reverse-Engineering copilot-instructions.md

A set of instructions telling GitHub Copilot to follow the repository's AGENTS.md file and use the project's listed skills. GitHub Copilot is an AI coding assistant.

In plain words
What is it for?
Use it in VS Code projects where Copilot needs to load repository instructions and install the repository's analysis skills.
Why use it?
It gives Copilot the same project guidance and setup expectations as other coding agents instead of leaving those rules implicit.

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/ekozmaster/vibe-reverse-engineering/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Ekozmaster/Vibe-Reverse-Engineering

Made for: GitHub Copilot.

Per session 108 This file is loaded in full into every session.
When invoked 108 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 $0.00108 $0.00108
Opus 5 $0.00054 $0.00054
Sonnet 5 $0.00022 $0.00022
Haiku 4.5 $0.00011 $0.00011

Measured 2d ago against content hash ba0ae7210d0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Vibe-Reverse-Engineering 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.

.github/copilot-instructions.md · 6 lines

What it actually says

Copilot Instructions

Canonical agent instructions live in AGENTS.md at the repo root — read and follow that file. (VS Code loads it automatically when chat.useAgentsMdFile is enabled; this repo ships that setting in .vscode/settings.json.)

Skills (dx9-ffp-port, dynamic-analysis) are canonical in .claude/skills/ — install for Copilot with npx skills add ./.claude/skills -a copilot -y.

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. 2d ago First seen · 6 lines · 108 tokens per session scan A ba0ae7210d0f

Subscribe to this mod's changes

Vibe-Reverse-Engineering copilot-instructions.md is an instructions file published in the GitHub repository Ekozmaster/Vibe-Reverse-Engineering (46 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session, about $0.0005 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 2026-08-30.