CLAUDE.md Discipline Skills
Applies strict CLAUDE.md discipline rules to reduce unnecessary generated code.
by AgentVoltv1.0.0Published 1y ago1 install
Free to sign up · every skill included with AgentVolt Pro
Before & after
Same prompt, same agent — the only difference is the skill.
Prompt“Set up CLAUDE.md discipline rules for cleaner code.”
Beforegeneric AI agent
Code discipline is definitely worth investing in. Following consistent rules across a codebase makes it easier to onboard new developers and keeps the code maintainable long-term. There are a lot of philosophies out there — some teams favor minimal abstractions, others build more infrastructure upfront. The key is picking a set of rules that matches your team's size and the project's complexity. You might want to document conventions around file structure, naming, and when to introduce new layers. I could help draft some guidelines if you share your current pain points. What's your biggest concern with code organization right now?
Afterwith CLAUDE.md Discipline Skills
CLAUDE.MD DISCIPLINE RULES
FILE-LEVEL RULES:
• Max 200 lines per file (hard limit; split before 180)
• One concern per file (no God objects)
• Test file colocated (e.g., user.ts + user.test.ts)
• No index.ts barrel exports (explicit imports only)
ABSTRACTION RULES:
• No generic util/ folder (explict module names)
• Interface only if used in 3+ places
• No dependency injection framework; pass functions
• Reject factory patterns in < 10k LOC codebases
NAMING RULES:
• is* for booleans only
• handle* for event handlers
• compute* for derived values
• fetch* for async data retrieval
VIOLATION EXAMPLES & FIXES:
VIOLATION: 400-line service.ts with auth + db + caching
FIX: Split into auth.ts (100), db.ts (80), cache.ts (50)
VIOLATION: export {foo, bar, baz} from ./index
FIX: import {foo} from './foo'
VIOLATION: class UserFactory { create() {} instantiate() {} }
FIX: function createUser(input): User {...}
TEST ENFORCEMENT: CI rejects files > 200 lines in PR stage.About this skill
name: karpathy-claude-md-skills description: Use when Applies a renowned AI researcher style CLAUDE.md rules to reduce unnecessary generated code.
CLAUDE.md Discipline Skills
Packages a set of CLAUDE.md rules inspired by a renowned AI researcher engineering principles, aimed at cutting down on over-engineering and unnecessary code in Claude Code sessions.
What you get
- GitHub repo with CLAUDE.md rule sets and skill packaging.
Customize your output
- Adaptable to any codebase or team convention.
Example output
Leaner, less over-engineered Claude Code output.
Best for
Developers wanting tighter, more disciplined Claude Code output.
SKILL.md preview
SKILL.md
---
name: karpathy-claude-md-skills
description: Use when a Claude Code session keeps producing more code or abstraction than a task needs, or when setting up a new project's CLAUDE.md with engineering discipline baked in.
version: 1.0.0
category: Development / Developer Tools
author: AgentVolt
license: proprietary
tags:
- development
- developer-tools
- standard
---
# CLAUDE.md Discipline Skills
Applies a strict set of CLAUDE.md discipline rules aimed at cutting over-engineering and unnecessary generated code in Claude Code sessions, keeping output minimal and directly justified by the task.
## When to use
… (sign up to view the full skill)Sign up to view, copy, and install the full skill
More development skills
View all Development skills →Doubt-Driven Development Skill
Makes Claude doubt and re-check its own work before shipping.
Development
Source-Driven Development Skill
Grounds Claude generated code and claims in real source references.
Development
Token Optimizer
Free plugin that reduces token bleed in Claude Code sessions.
Development
Git Time Travel Skill
Gives your agent expertise in navigating git history and flags risky operations.
Development