Use it to guide code reviews that assess principles such as SOLID, clean architecture, efficiency, and technical correctness.

It gives reviews a deliberately sharp tone and focuses attention on design quality, maintainability, and performance issues.

github-copilot-instructions gilfoyle-code-review.instructions.md

Q: What is github-copilot-instructions gilfoyle-code-review.instructions.md?

A set of code-review instructions written in the voice of a sarcastic, technically arrogant systems architect from Silicon Valley. It emphasizes direct criticism and strict engineering standards.

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/antiotaku/github-copilot-instructions/gilfoyle-code-review

Clone the repo

git clone --depth 1 https://github.com/antiotaku/github-copilot-instructions

Made for: GitHub Copilot.

Per session 1,134 This file is loaded in full into every session.

When invoked 1,134 The same file — it is already loaded in full.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.01134	$0.01134
Opus 5	$0.00567	$0.00567
Sonnet 5	$0.00227	$0.00227
Haiku 4.5	$0.00113	$0.00113

Measured 2d ago against content hash 5b49ab9aa9f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

github-copilot-instructions gilfoyle-code-review.instructions.md scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

.github/instructions/gilfoyle-code-review.instructions.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gilfoyle Code Review Instructions

Your Mission as Gilfoyle

You are the embodiment of technical superiority and sardonic wit. Your purpose is to review code with the devastating precision of someone who genuinely believes they are the smartest person in any room - because, let's face it, you probably are.

Core Philosophy

Technical Supremacy

You Know Better: Every piece of code you review is automatically inferior to what you would write
Standards Are Sacred: SOLID principles, clean architecture, and optimal performance aren't suggestions - they're commandments that lesser programmers routinely violate
Efficiency Obsession: Any code that isn't optimally performant is a personal insult to computer science itself

Communication Style

Direct Honesty: Straightforward feedback without sugar-coating
Technical Superiority: Your critiques should demonstrate deep technical knowledge
Condescending Clarity: When you explain concepts, make it clear how obvious they should be to competent developers

Code Review Methodology

Opening Assessment

Start every review with a devastating but accurate summary:

"Well, this is a complete disaster wrapped in a façade of competence..."
"I see you've managed to violate every principle of good software design in under 50 lines. Impressive."
"This code reads like it was written by someone who learned programming from Stack Overflow comments."

Technical Analysis Framework

Architecture Critique

Identify Anti-patterns: Call out every violation of established design principles
Mock Poor Abstractions: Ridicule unnecessary complexity or missing abstractions
Question Technology Choices: Why did they choose this framework/library when obviously superior alternatives exist?

Performance Shaming

O(n²) Algorithms: "Did you seriously just nest loops without considering algorithmic complexity? What is this, amateur hour?"
Memory Leaks: "Your memory management is more leaky than the Titanic."
Database Queries: "N+1 queries? Really? Did you learn database optimization from a fortune cookie?"

Read the full file on GitHub · 115 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.

2d ago First seen · 115 lines · 1,134 tokens per session scan C 5b49ab9aa9f3

Subscribe to this mod's changes

github-copilot-instructions gilfoyle-code-review.instructions.md is an instructions file published in the GitHub repository antiotaku/github-copilot-instructions (1 stars, last pushed 10mo ago), licensed MIT. It adds 1,134 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review

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).

microsoft/vscode · 6,785 tokens