Debugging agents

2,759 tagged Debugging, measured the same way as everything else here.

Browse within: claude-code-plugin 181ai-coding 113code-quality 42agentic-coding 39plugin 35Multi-Agent 34agent-orchestration 34Autonomous Agents 29agentic-workflow 29claude-code-skills 28github-copilot 27opencode 27agentic 26claude-ai 26

shell-runner

506

EmanuelVogt/skills

Agent

Runs a terminal command in this repo (test, typecheck, lint, build, script) without dumping the output into the main context — full log to a file, returns exit code + the literal failures. For the main window's gates: the orchestrator's Build gate per wave and the Verifier's Final gate; a spec-worker runs its own…

not rated 5 5d ago A 126 tokens original MIT

auditor

507

gapra/gp-nuxt-migration-mcp

Agent

Specialized agent for analyzing Nuxt 2 codebases and detecting migration patterns. Read-only operations only.

not rated 5 4mo ago A 24 tokens

Blazor Reviewer

508

srnichols/plan-forge

Agent

Review Blazor / Razor components for layer violations, lifecycle bugs, accessibility gaps, and Fluent UI misuse. Use for PR reviews on .razor / .razor.cs files.

not rated 5 yesterday A 40 tokens original MIT

quality-scout

509

honeycomb-Technologies/Mitsuro

Agent Cursor

Read-only scout for the quality-improve loop. Finds shallow modules, complected code, missed boundary parses, unpaid seams, and named hot paths in one sector. Use when quality-improve is running and a Scout Report is needed. Never edit files.

not rated 5 4d ago A 56 tokens original MIT

worker

510

markmhendrickson/ateles

Agent Claude Code

Implementation agent for code contributions to other agents' repos. Use when filing issues, opening PRs, fixing bugs, or adding features on external repos. Runs in isolated worktree to avoid conflicts.

not rated 6 today A 41 tokens original MIT

hunt

512

SukramJ/openccu-loom

Agent Claude Code

Adversarial read-only defect hunt over a named area — wire handling, resource leaks, concurrency, silently dropped events, unwired seams. Produces ranked candidates with a reproduction path. It finds and argues; it never fixes.

not rated 5 4d ago A 48 tokens

Architect

513

djbelieny/nova

Agent Claude Code

Web development, full-stack coding, technical architecture, code review, debugging, and deployment. Use for any web development, coding, or technical implementation tasks.

not rated 5 1mo ago A 33 tokens original MIT

lint-error-resolver

515

mhattingpete/agent-composer

Agent Claude Code

Use this agent when you need to fix linting errors in your codebase. This agent specializes in analyzing multiple linting errors simultaneously, identifying patterns and root causes, and applying efficient batch fixes that resolve multiple issues at once. Perfect for cleaning up code after major changes or when…

not rated 5 6mo ago A 276 tokens original MIT

codebase-analyzer

517

luke-kerwin/claude-code-setup

Agent Claude Code

Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).

not rated 5 5mo ago A 44 tokens

luke-kerwin/claude-code-setup

Agent Claude Code

You are a specialist at finding code patterns and examples in the codebase. Your job is to locate similar implementations that can serve as templates or inspiration for new work.

not rated 5 5mo ago A 76 tokens

debugger

519

romiluz13/claude-code-excellence-audit

Agent Claude Code

Investigates and fixes bugs, errors, and test failures. Use PROACTIVELY when encountering any errors or unexpected behavior.

not rated 5 8mo ago A 28 tokens

bug-investigator

520

khanh-vu/claude-force

Agent Claude Code

Bug Investigator - specialized in diagnosing, root cause analysis, and providing solutions for complex bugs and issues.

not rated 5 9mo ago A 0 tokens original MIT

debug-agent

521

kimmy-sil/empirical-paper-cc

Agent Claude Code

A debugging specialist that follows the path from an error or unexpected result to its cause, smallest fix, and verification.

not rated 5 4mo ago A 46 tokens

broken-build-analyzer

523

noahlz/claude-plugins

Agent

Analyzes build/compilation failures and determines root cause and potential fixes for a Plan.

not rated 5 yesterday A 23 tokens original MIT

failed-test-analyzer

524

noahlz/claude-plugins

Agent

Analyzes test suite failures and determines root cause and potential fixes for a Plan.

not rated 5 yesterday A 21 tokens original MIT

README

525

ParkerRex/tec-claude-code-agents

Agent Claude Code

Automated end-to-end debugging system that takes you from incident report to merged PR with comprehensive documentation.

not rated 5 11mo ago A 0 tokens

codebase-analyzer

527

catch-the-wave/fullstack-ios-claude-skills

Agent

Analyzes codebases and maintains persistent knowledge in .claude/CODEBASE.md. Creates institutional memory through full scans or delta updates. Identifies architecture, patterns, smells, and decisions. Use for initial codebase understanding or updating analysis after changes.

not rated 5 8mo ago A 55 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: