Debugging

15,549 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

codex-reconnect-repair

1009

9398-haha/codex-reconnect-repair

Skill Claude CodeCodex

Diagnose and safely repair Codex "Reconnecting... 1/5" through "5/5" loops in the CLI, desktop app, or IDE on macOS, Linux, and Windows. Use when a Codex turn stalls on repeated stream reconnects or only succeeds after HTTPS fallback; do not use for generic login, quota, model, or rate-limit errors.

not rated 5 13d ago A 83 tokens original MIT

openfoam-sim

1010

svd-ai-lab/sim-plugin-openfoam

Skill Claude CodeCodex

Use when the user asks Codex, Claude Code, or another AI coding agent to run, inspect, or debug OpenFOAM cases through sim-cli. Supports case checks, solver execution, log inspection, result artifacts, replayable CFD workflows, and benchmark tasks.

not rated 5 4mo ago A 58 tokens original Apache-2.0

RULE

1011

CacinieP/network-troubleshoot-skill

Cursor rule Cursor

Network troubleshooting — systematic diagnosis and resolution for connectivity, DNS, proxy, SSL, HTTP errors.

not rated 5 1mo ago A 682 tokens original MIT

quiz-me

1012

emanzurv/quiz-me-skill

Plugin Claude Code

Bundles 1 skill, 2 commands, 2 hooks · 125 tokens together

Gates code changes behind an interactive quiz: Claude investigates, tests your understanding of root cause and fix, and only implements once you pass.

not rated 5 changed 2d ago A tokens not measured original MIT

codegraph

1013

lzehrung/codegraph

Skill Claude CodeCodex

Use for repo structure, symbol navigation, dependency analysis, duplicate triage, and PR impact review when plain text search is too shallow.

not rated 5 +1 changed today A 30 tokens original MIT

TeamManagementPlugin/claude-plugin

Skill Claude CodeCodex

Systematic debugging — a four-phase root-cause methodology, boundary instrumentation for multi-component systems, the 3-fix escalation rule, and a verification gate to run before claiming anything is fixed. Use on any test failure, production bug, build failure, performance regression, or integration glitch, and…

not rated 5 +1 1mo ago A 95 tokens original MIT

bug-report

1015

Kepsilent/Bug-Report-Skill

Skill Claude CodeCodex

A general bug-diagnosis toolkit for apps that use the included BugReport logging library. It collects error and network logs, traces crashes, monitors performance, and helps prepare structured reports.

not rated 5 3mo ago A 4 tokens original MIT

vconsole-mcp

1017

Simonmie/vConsole-MCP

MCP server Claude CodeCodexCursor +2

MCP server "vconsole-mcp" as configured in Simonmie/vConsole-MCP. Runs locally from the vconsole-mcp npm package.

not rated 5 11d ago A tokens not measured original MIT

windbg-mcp

1018

kanren3/windbg-mcp

MCP server Claude CodeCodexCursor +2

MCP server that drives cdb.exe/kd.exe (WinDbg): crash dump analysis, live user-mode debugging, and kernel debugging. Runs locally from the windbg-mcp npm package.

not rated 5 26d ago A tokens not measured original MIT

builder

1019

iuliandita/agents

Agent Claude Code

Bounded editor for a specified change to named files with named check commands. Returns a diff receipt. Refuses design decisions and unnamed files.

not rated 5 changed yesterday A 30 tokens original MIT

sentry

1020

getsentry/plugin-claude

Plugin Claude Code

Bundles 8 skills · 634 tokens together

Sentry Plugin for Claude Code to help with debugging including MCP and skill capabilities.

not rated 4 today A tokens not measured original MIT

qualityclouds/qualityclouds

MCP server Claude CodeCodexCursor +2

Secure MCP runtime server for scanning and autofixing code issues. Remote server at mcp.qualityclouds.com.

not rated 4 1mo ago A tokens not measured

debugium

1023

Algiras/debugium

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 67 tokens together

AI-driven debugger for Python, JavaScript, TypeScript, Rust, Java, C/C++, Scala, and WebAssembly. Control live debug sessions via MCP tools: launch or attach to processes, set breakpoints, inspect variables, step through execution, evaluate expressions, and trace bugs using DAP adapters.

not rated 4 5mo ago A tokens not measured

feedthrough

1025

feedthrough/feedthrough

MCP server Claude CodeCodexCursor +2

Debug bridge inside your web app: an agent reads the DOM, console and network. Any browser. Runs locally from the @feedthrough/mcp npm package. Needs 2 environment variables to run.

not rated 4 6d ago A tokens not measured original MIT

cdeust/ai-architect-mcp-codebase

Plugin Claude Code

Bundles 3 skills, 24 commands, 18 agents, 6 hooks, 2 MCP servers · 597 tokens together

Rust MCP server that indexes ANY codebase into a LadybugDB property graph — source in 11 languages with full AST, plus docs/config/binaries as File nodes (.js→Imports, Markdown→References). Resolves imports and call chains, detects communities via Leiden, traces execution flows from entry points, and exposes 26 MCP…

not rated 4 today A tokens not measured original MIT

openocd-mcp

1027

microhenrio/openocd-mcp

MCP server Claude CodeCodexCursor +2

MCP server to debug microcontrollers from Claude through OpenOCD (flash, halt/step, memory/registers, breakpoints, variables and peripheral registers by name). Runs locally from the openocd-mcp Python package. Needs 3 environment variables to run.

not rated 4 2mo ago A tokens not measured original MIT

mcp

1028

dev-proxy-tools/mcp

MCP server Claude CodeCodexCursor +2

MCP server for Dev Proxy that enables AI assistants to interact with Dev Proxy. Runs locally from the @devproxy/mcp npm package.

not rated 4 17d ago A tokens not measured original MIT

plumb-diagnose

1029

plumbkit/plumb

Skill Claude CodeCodex

Work out why a plumb call was refused, or why a change looks broken — read the rejection, get compile truth from diagnostics, and check the daemon and index before blaming the code. Use when a tool call fails or a result looks wrong.

not rated 4 yesterday A 56 tokens original MIT

screenshots

1030

xAmirHamza77/ReverseOps-Skill

Skill Claude CodeCodex

Advanced UI analysis and interaction through pixel-level reasoning to solve complex interaction problems, locate hard-to-find elements, verify visual states, and debug layout/rendering issues. Use as needed after UI Mapper inspection when advanced reasoning or non-standard views are required.

not rated 4 1mo ago A 52 tokens original MIT

ast-code-graph

1031

rolandbrecht/agent-skills

Skill Claude CodeCodex

Use this skill ANY time you need to search for code structure, refactor symbols, analyze impact, find dead code, or trace dependencies. ALWAYS invoke BEFORE using grep for structural code analysis. Trigger categories: structural pattern search (e.g. useEffect without deps, async without try-catch, fetch calls outside…

not rated 4 28d ago A 196 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: