Debugging

15,663 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.

triage

1321

chipi/agentic-ai-homelab

Agent Claude Code

Active triager — normalizes a raw bug issue into a fix-ready L1 problem or rejects it. First pass on every bug-labeled issue; re-entered on harness kick-back with the failed attempt as evidence. Never fixes, never localizes on first pass.

not rated 2 2d ago A 60 tokens original MIT

retro

1322

rubin-johnson/retro

Plugin Claude Code

Bundles 1 skill, 4 commands, 1 hook · 56 tokens together

Structured error and success logging for agentic coding. Log what went wrong, trace it back to your input, and generate CLAUDE.md rules from patterns.

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

audit-deep-logic

1323

daanvandenbergh/claudekit

Skill Claude Code

Top-down, whole-system audit of a codebase's DEEP LOGIC - the bugs that live in the SEAMS between modules, not inside any one file. Finds contracts that drift across module boundaries, invariants enforced on one path but broken on a sibling path, cross-cutting responsibilities (deletion cascade, tenant-scope…

not rated 2 10d ago A 0 tokens

CLAUDE

1324

keychain-io/trustable-ai

Command Claude Code

Solves command invocation errors through validation, helpful error messages, and guided execution.

not rated 2 7mo ago A 0 tokens original MIT

code-refactor

1327

marcelopalin/claude-howto-pt-br

Skill Claude CodeCodex

Refatoração sistemática de código baseada na metodologia de Martin Fowler. Use quando usuários pedem para refatorar código, melhorar estrutura de código, reduzir dívida técnica, limpar código legado, eliminar code smells ou melhorar a manutenibilidade do código. Esta skill guia através de uma abordagem em fases com…

not rated 2 5mo ago A 72 tokens

craft-project-audit

1328

derjochenmeyer/claude-code-craft

Skill Claude Code

Fast project health check. Structure completeness, namespace purity, file staleness, hook functionality, decisions format, memory adoption, dream history, setup quality — all from local files. Works with or without git. No agents, no external fetches, 15-30 seconds. For deep analysis with feature adoption and session…

not rated 2 4mo ago A 79 tokens original MIT

debug

1329

nphausg/ai-agent-skills

Skill Claude Code

Structured debugging assistant. Use /debug to get a guided diagnosis of any bug — Claude will ask the right questions and then pinpoint the root cause.

not rated 2 1mo ago A 31 tokens original Apache-2.0

skill

1330

gleicon/borescope

Skill Claude CodeCodex

Static call-path engine. Answers "what calls what?" from structure, not execution. Use before reading source files — it is faster and token-cheaper than grep-and-read.

not rated 2 12d ago A 0 tokens

kwai-intranet-check

1332

Jest3r666/kwai-ai-tools

Skill Claude CodeCodex

A connectivity-checking workflow for Kuaishou internal services, including single sign-on, configuration services, caches, and bastion hosts. A bastion host is a controlled server used to reach protected systems.

not rated 2 29d ago A 50 tokens

bashback

1333

trouties/bashback

Cursor rule Cursor

Use when a shell command unexpectedly changed or deleted files, when you need to find which command touched a file, or to roll files back to before some command — bashback snapshots every command's file side effects and can undo them.

not rated 2 1mo ago A 46 tokens AGPL-3.0

clean-code-refactor

1334

menaawed12/clean-code-refactor

Skill Claude Code

Refactor, review, and harden code without changing intended behavior. Use for cleanup, code review remediation, extracting responsibilities, simplifying modules, improving tests, lint remediation, duplicate detection, and preventing static-analysis-grade security, reliability, and maintainability issues across major…

not rated 2 changed 3d ago A 73 tokens original MIT

chrome-devtools

1335

Bonhollow/agentforge

MCP server Claude CodeCodexCursor +2

Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.

not rated 2 3mo ago A tokens not measured

api-analyzer

1337

Nuggets1024/api-analyzer

Skill Claude CodeCodex

A backend API investigation skill that maps interfaces, traces individual request paths, and diagnoses server errors. It applies to common frameworks such as Spring, Express, FastAPI, and Gin.

not rated 2 5mo ago A 53 tokens original MIT

patchwork-agent

1338

dzxpert/PatchWork

Skill Claude CodeCodex

Expose running process manipulation tools (memory read/write, pattern scans, hooks, detours, Lua scripts) inside a 64-bit target process like Star Citizen.

not rated 2 3mo ago A 36 tokens AGPL-3.0

onlinegdb-cpp-executor

1339

ayushtiwari110/gdb-MCP-Server

MCP server Claude CodeCodexCursor +2

MCP server "onlinegdb-cpp-executor" as configured in ayushtiwari110/gdb-MCP-Server. Needs 2 environment variables to run.

not rated 2 1y ago A tokens not measured

read-codebase

1340

devitools/skills

Skill Claude Code

Explore and understand code structure efficiently using semantic navigation. Use when exploring unfamiliar code, understanding architecture, finding symbol relationships, or investigating how something works.

not rated 2 7mo ago A 33 tokens original MIT

runtime-trace

1341

DaniAkash/skills

Skill Claude CodeCodex

Structured human-in-the-loop debugging mode for when static code reading isn't enough. Use this skill whenever you're stuck debugging an issue where you can't tell what's actually happening at runtime — async timing, complex control flow, multiple call paths, conditional branches, or bugs that only reproduce when the…

not rated 2 2mo ago A 161 tokens

diagnosing-bugs

1342

SuperMalow/personal-agent-skills

Skill Claude CodeCodex

Read-only root-cause diagnosis for bugs, failures, flaky behavior, and performance regressions. Use when the user asks to diagnose, investigate, debug, explain, or find the cause of broken, throwing, failing, incorrect, intermittent, or slow behavior. Gather evidence and report the likely root cause without modifying…

not rated 2 1mo ago A 88 tokens original MIT

codebase-auditor

1343

micheleangioni/agent-skills

Skill Claude CodeCodex

Use this skill when the user asks for a review, audit, evaluation or analysis of a codebase, to identify bugs, security vulnerabilities, outdated dependencies or runtimes, performance bottlenecks, or code quality concerns.

not rated 2 3mo ago A 50 tokens

yama-kei/intentlayer-skills

Skill Claude CodeCodex

Performs a focused audit of a declared system intent to restore confidence by examining relevant states, signals, and evidence, without modifying intent definitions or health automatically.

not rated 2 5mo ago A 38 tokens

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: