surgeon

Apply minimal, scoped code changes to fix bugs or implement features.

Updated Feb 23, 2026
One-click install
npx skills add https://github.com/mcevoyinit/agentic-skills --skill surgeon-mcevoyinit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: surgeon
Source: https://github.com/mcevoyinit/agentic-skills/tree/main/skills/coding-modes/surgeon
Command: npx skills add https://github.com/mcevoyinit/agentic-skills --skill surgeon-mcevoyinit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Minimal-change coding mode. Touch only what was asked. No refactoring nearby code, no adding comments to unchanged functions, no "improvements" beyond scope. The smallest diff that solves the problem. In and out.

Core Features & Use Cases

  • Touch only the minimal required parts of the code to fix issues or implement features.
  • Enforce strict scope so surrounding code remains untouched and review is straightforward.
  • Use Case: When you're under time pressure to fix a bug in a large codebase without introducing unintended changes.

Quick Start

Identify the problem, locate the relevant code, and implement the minimal change that fixes the bug without touching unrelated logic.

Frequently Asked Questions about surgeon

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fix a bug in a large codebase without introducing unintended changes?

To fix a bug without unintended changes, apply surgically scoped edits that touch only the minimal required code. This enforces strict scope so surrounding logic remains untouched, ensuring the smallest diff that solves the problem.

What is minimal-change code editing and when should I use it?

Minimal-change code editing is a deterministic approach that makes the smallest possible change to fix issues or implement features. Use it for hotfixes and incremental improvements in large repositories where safety and auditability are priorities.

How do I implement a feature while preventing scope creep in the code?

To prevent scope creep when implementing a feature, enforce strict one-change-per-task discipline. This means no refactoring nearby code, no adding comments to unchanged functions, and no improvements beyond the requested scope.

Does this code review approach support hotfixes in large repositories?

Yes, this deterministic code review approach supports hotfixes in large repositories by applying minimal, well-scoped changes to individual functions or small code regions. This ensures clear justification and straightforward review.

What are the limitations of making only the smallest possible code change?

The limitation of making the smallest possible code change is that you cannot refactor nearby code or add improvements beyond scope. It enforces strict one-change-per-task discipline, preventing broader code cleanup during a bug fix.