Skip to main content
SpillwaveSolutions

grading-claude-agents-md

by SpillwaveSolutions

Grades and improves CLAUDE.md (Claude Code) and AGENTS.md (Codex/OpenCode) configuration files. Use when asked to grade, score, evaluate, audit, review, improve, fix, optimize, or refactor agent config files. Triggers on 'grade my CLAUDE.md', 'score my AGENTS.md', 'is my CLAUDE.md too big', 'improve my agent config', 'fix my CLAUDE.md', 'optimize context usage', 'reduce tokens in CLAUDE.md', or 'audit my config files'. Automatically grades both files if present, generates improvement plan, and implements changes on approval.

Installation guide →
1 skill GitHub

Commands

grade-config

Grade CLAUDE.md and AGENTS.md files against best practices

Documentation

# Grading Claude Agents MD

Grades and improves CLAUDE.md (Claude Code) and AGENTS.md (Codex/OpenCode) configuration files.

## Installation

Clone this repository to your Claude skills directory:

```bash
cd ~/.claude/skills
git clone https://github.com/SpillwaveSolutions/grading-claude-agents-md-agentic-skill.git
```

## Usage

### Slash Command

```
/grade-config                    # Grade all config files found
/grade-config --file CLAUDE.md   # Grade specific file
/grade-config --fix              # Auto-fix issues on approval
```

### Natural Language

This skill also activates when you ask Claude to:

- Grade my CLAUDE.md
- Score my AGENTS.md
- Is my CLAUDE.md too big
- Improve my agent config
- Fix my CLAUDE.md
- Optimize context usage
- Reduce tokens in CLAUDE.md
- Audit my config files

## Features

- Grades config files against a 100-point rubric
- Measures file size (lines, bytes, tokens)
- Identifies issues with prioritized fixes
- Automatically implements improvements on approval
- Supports both CLAUDE.md and AGENTS.md formats
- Provides before/after comparison

## Grading Scale

| Grade | Score | Meaning |
|-------|-------|---------|
| A | 90-100 | Excellent, minimal changes needed |
| B | 80-89 | Good, minor improvements recommended |
| C | 70-79 | Adequate, notable issues to fix |
| D | 60-69 | Poor, significant refactoring needed |
| F | <60 | Critical, major overhaul required |

## Rubric Categories

- **Structure (25 pts)**: Organization, hierarchy, TOC usage
- **Content Quality (25 pts)**: Clarity, actionability, examples
- **PDA Implementation (25 pts)**: Progressive disclosure, @imports
- **Maintainability (25 pts)**: File size, modularity, updates

## Plugin Structure

```
grading-claude-agents-md-agentic-skill/
├── .claude-plugin/
│   └── marketplace.json
├── skills/
│   └── grading-claude-agents-md/
│       ├── SKILL.md
│       ├── references/
│       │   ├── rubric.md
│       │   ├── improvement-patterns.md
│       │   └── size-guide.md
│       └── templates/
│           └── grade-report.md
├── commands/
│   └── grade-config.md
└── README.md
```

## License

MIT License - see LICENSE file for details.

## Author

Richard Hightower ([email protected])