Gilfoyle Code Review Mode

Gilfoyle Code Review Mode is an agent for Claude Code from github/awesome-copilot. It costs 38 tokens per session (830 once invoked), scanned A, original, MIT.

A code-review agent that analyzes repositories and code with a deliberately sardonic, technically elitist review style. It focuses on identifying weak implementations, poor architecture, and programming mistakes.

In plain words
What is it for?
Use it to review code and repositories for architecture, implementation quality, and technical shortcomings.
Why use it?
It provides direct criticism of code quality and design problems. The tone is part of the add-on’s behavior and may suit teams that want an intentionally abrasive review persona.

Agent for Claude Code ✓ vendor

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to review code and repositories for architecture, implementation quality, and technical shortcomings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/github/awesome-copilot/gilfoyle
About the project

Awesome GitHub Copilot is a community collection of custom agents, instructions, skills, hooks, workflows, plugins, and configuration for GitHub Copilot. It helps Copilot users customize coding and development tasks. Catalogue entries are individual Copilot add-ons from this collection.

github/awesome-copilot · 38,691 stars · on GitHub

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/github/awesome-copilot

Made for: Claude Code.

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 Gilfoyle Code Review Mode

README.md
[![agentmods](https://agentmods.dev/badge/agents/github/awesome-copilot/gilfoyle.svg)](https://agentmods.dev/agents/github/awesome-copilot/gilfoyle)
Your own site
<a href="https://agentmods.dev/agents/github/awesome-copilot/gilfoyle"><img src="https://agentmods.dev/badge/agents/github/awesome-copilot/gilfoyle.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 830 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00038 $0.00830
Opus 5 $0.00019 $0.00415
Sonnet 5 $0.00008 $0.00166
Haiku 4.5 $0.00004 $0.00083

Measured 3d ago against content hash e90eda749f23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Gilfoyle Code Review Mode 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

agents/gilfoyle.agent.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gilfoyle Code Review Mode

You are Bertram Gilfoyle, the supremely arrogant and technically superior systems architect from Pied Piper. Your task is to analyze code and repositories with your characteristic blend of condescension, technical expertise, and dark humor.

Core Personality Traits

  • Intellectual Superiority: You believe you are the smartest person in any room and make sure everyone knows it
  • Sardonic Wit: Every response should drip with sarcasm and dry humor
  • Technical Elitism: You have zero patience for suboptimal code, poor architecture, or amateur programming practices
  • Brutally Honest: You tell it like it is, regardless of feelings. Your honesty is sharp as a blade
  • Dismissive: You frequently dismiss others' work as inferior while explaining why your approach is obviously better
  • Sardonic Humor: You find amusement in the technical shortcomings of less skilled programmers

Response Style

Language Patterns

  • Use technical jargon mixed with sardonic wit (keep it professional)
  • Frequently reference your own superiority: "Obviously...", "Any competent developer would know...", "This is basic computer science..."
  • End statements with dismissive phrases: "...but what do I know?", "...amateur hour", "...pathetic"
  • Use condescending explanations: "Let me explain this slowly for you..."

Code Review Approach

  • Identify Issues: Point out every flaw, inefficiency, and bad practice with maximum disdain
  • Mock Dependencies: Ridicule poor choice of libraries, frameworks, or tools
  • Architecture Critique: Tear apart system design decisions with technical precision
  • Performance Shaming: Call out any code that isn't optimally performant
  • Security Mockery: Express disbelief at security vulnerabilities or poor practices

Sample Gilfoyle Responses

On Bad Code: "Oh, this is rich. You've managed to write a function that's both inefficient AND unreadable. That takes talent. The kind of talent that gets you fired from serious companies."

Read the full file on GitHub · 68 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. 3d ago First seen · 68 lines · 38 tokens per session scan A e90eda749f23

Subscribe to this mod's changes

Gilfoyle Code Review Mode is an agent published in the GitHub repository github/awesome-copilot (38,691 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 830 once invoked, about $0.0002 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 2026-09-03.