---
slug: "claude-code-misc"
source_type: "readme"
source_url: "https://cdn.jsdelivr.net/gh/delexw/claude-code-misc@main/README.md"
repo: "https://github.com/delexw/claude-code-misc"
source_file: "README.md"
branch: "main"
---
# Claude Code Misc Configurations

## 1. Meta-Prompter MCP

![eval-opt](https://github.com/delexw/claude-code-misc/raw/HEAD/workflow.jpg)

**Location**: `.claude/mcp/meta-prompter/`

A prompt evaluation tool available as both an MCP server and a standalone CLI. Grades prompts and returns JSON-only analysis across 8 dimensions (clarity, specificity, context, actionability, safety, testability, hallucination prevention, token efficiency) with weighted global scoring.

**Key Features**:
- Temperature-controlled evaluation (0 vs Claude Code's default 1)
- Machine-readable JSON output for agentic workflows
- Built-in result viewer with `eval-viewer.html`
- Support for multiple AI providers (Anthropic, OpenAI)

See [meta-prompter README](https://github.com/delexw/claude-code-misc/blob/HEAD/.claude/mcp/meta-prompter/README.md) for setup and usage.

## 2. Commands
**Location**: `.claude/commands/`

- **`/debug-partner`** - AI-assisted debugging partner for systematic troubleshooting
  - Evidence-based investigation with code-centric traces
  - Progressive clarification and hypothesis testing
  - Includes specific file names, function names, and line numbers
  - Collaborative approach with verification at each step

## 4. StatusLine
**Location**: `.claude/statusline/`

Context monitoring script (`ctx_monitor.js`) that displays real-time usage:
- Context window usage percentage (0-200k tokens) with color coding (green/yellow/red)
- Session ID and token consumption tracking
- Model name and usage statistics
- Automatic synthetic message filtering

![statusline](https://github.com/delexw/claude-code-misc/raw/HEAD/statusline.png)

## Links

[![Hypercommit](https://img.shields.io/badge/Hypercommit-DB2475)](https://hypercommit.com/claude-code-misc)