Skip to main content
plugin

debugging-toolkit — Claude Code plugin: what it does, how to install

debugging-toolkit adds the /smart-debug command and two subagents to Claude Code for root cause analysis and workspace tuning. Useful when investigating test failures or production errors.

MIT ★ 126 updated 2026-10-04

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add Ormus-Solutions/LibreUIUX-Claude-Code
/plugin install debugging-toolkit@libreuiux
Open on GitHub

What debugging-toolkit does

The plugin provides two specialized subagents (debugger and dx-optimizer) along with the /smart-debug command. Both subagents run on the haiku model, keeping token consumption low during routine work. The debugger agent isolates stack traces and verifies minimal code fixes. The dx-optimizer agent automates Git hooks and project onboarding workflows.

The /smart-debug command runs a 10-phase troubleshooting process. It collects metrics from tools like Sentry or DataDog, ranks hypotheses by probability, and prepares regression tests. Gathering telemetry requires access to active monitoring integrations in your project.

What it helps with

  • Isolate the root cause of test failures from stack traces
  • Collect error telemetry from Sentry, DataDog, or Jaeger
  • Streamline developer onboarding and workspace setup
  • Generate regression tests to prevent bug recurrence

Example prompts for the agent

  • /smart-debug Intermittent 504 timeout errors in checkout flow affecting 5% of users
  • /smart-debug Unit test test_auth_token fails with NullPointerException after dependency bump

How to install debugging-toolkit

Plugin marketplace

/plugin marketplace add Ormus-Solutions/LibreUIUX-Claude-Code
/plugin install debugging-toolkit@libreuiux

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about debugging-toolkit

How to install debugging-toolkit in Claude Code?

First, register the marketplace source by running /plugin marketplace add Ormus-Solutions/LibreUIUX-Claude-Code. Then, install the plugin using /plugin install debugging-toolkit@libreuiux.

What does debugging-toolkit do?

It delivers subagents for bug analysis and developer experience automation alongside a structured incident diagnosis command. The toolkit inspects stack traces, scores hypotheses, and validates code fixes.

Which AI model powers the plugin agents?

Both debugger and dx-optimizer use the haiku model. This keeps token usage economical during repetitive diagnostic tasks and environment configuration.

Source text

debugging-toolkit · MIT
# Debugging Toolkit

> Root cause analysis, developer experience optimization, and AI-assisted smart debugging workflows.

## Overview

The debugging-toolkit plugin provides agents and a command for systematic debugging and developer experience improvement. Use it when encountering errors, test failures, or unexpected behavior that needs root cause analysis, or when you want to reduce development friction through better tooling, workflows, and automation. The smart-debug command orchestrates a comprehensive AI-powered debugging workflow from triage through fix validation.

## Contents

### Agents

- **debugger** -- Debugging specialist for errors, test failures, and unexpected behavior. Captures error messages and stack traces, identifies reproduction steps, isolates failure locations, implements minimal fixes, and verifies solutions. Provides root cause explanations with evidence, specific code fixes, testing approaches, and prevention recommendations. Uses the `haiku` model.

- **dx-optimizer** -- Developer Experience (DX) specialist that reduces friction and automates repetitive tasks. Covers environment setup simplification (onboarding under 5 minutes), workflow automation (aliases, shortcuts, build optimization), tooling enhancement (IDE settings, git hooks, CLI commands), and documentation (setup guides, troubleshooting). Delivers measurable improvements to development velocity. Uses the `haiku` model.

### Commands

- **smart-debug** -- AI-assisted debugging workflow with 10 structured phases: initial triage with hypothesis generation, observability data collection (Sentry, DataDog, Jaeger), hypothesis ranking with probability scores, strategy selection (interactive, observability-driven, time-travel, chaos, statistical), intelligent instrumentation placement, production-safe techniques, root cause analysis, fix implementation with impact assessment, validation, and prevention through regression tests and monitoring.

## Usage

Install the plugin by adding it to your Claude Code configuration:

```bash
claude plugins add debugging-toolkit
```

Then invoke the command with your issue description:

```
/smart-debug Intermittent 504 timeout errors in checkout flow affecting 5% of users
```

## Related Plugins

- **error-debugging** -- Error-specific analysis with multi-agent review capabilities
- **error-diagnostics** -- Error classification, structured logging, and observability setup
- **distributed-debugging** -- Debugging across distributed systems and Kubernetes clusters

© Seth Hobson · MIT · Ormus-Solutions/LibreUIUX-Claude-Code

Similar plugins

All plugins for Testing and QA →

From the same set42

The whole set →
dependency-management dependency-management audits dependencies across eight ecosystems for CVEs and license issues, plus guides legacy code migration. Useful for security checks and framework upgrades. ★ 126repo stars full-review full-review runs a phased multi-agent code audit in Claude Code. Inspects architecture, OWASP vulnerabilities, runtime bottlenecks, and test suites. CX Codex +1 ★ 126repo stars full-stack-feature full-stack-feature runs feature work through four phases — schema design, API contracts, parallel implementation, testing — by delegating each step to a specialized subagent. Takes a feature description as its argument. CX Codex +1 ★ 126repo stars security-hardening The security-hardening command hardens an application through coordinated security agents. Use it to assess vulnerabilities, fix high-risk issues, and add layered controls. CX Codex +1 ★ 126repo stars performance-optimization performance-optimization coordinates end-to-end performance audits, database optimizations, frontend tuning, and load testing. CX Codex +1 ★ 126repo stars incident-response The incident-response command coordinates incident triage, investigation, mitigation, and recovery. Give it an incident description to start a staged response. CX Codex +1 ★ 126repo stars ui-responsive The ui-responsive command analyzes a component or page at five breakpoints and gives specific fixes for mobile, tablet and desktop layouts. CX Codex +1 ★ 126repo stars jungian-archetypes jungian-archetypes maps twelve brand archetypes to UI layout, typography, animations, and Tailwind styling. CX Codex +1 ★ 126repo stars

Project sponsors

Companies that keep this analytics open