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.

vg

1105

vibgrate/cli

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 26 tokens together

Vibgrate AI Context for Claude Code: a local-first MCP server with a deterministic code map (impact, navigation, search) plus version-correct, drift-annotated library docs. No API key.

not rated 3 today A tokens not measured original Apache-2.0

code-graph

1107

Nishant-Chaudhary5338/mcp-toolkit

MCP server Claude CodeCodexCursor +2

Index any TypeScript/React repo (incl. monorepos) into a queryable code graph — npx CLI, HTTP/WS server, and MCP server. Reverse queries (who-renders/who-calls/find-references), blast-radius, cycles, dead-code orphans, symbol signatures, external (nodemo. Runs locally from the code-graph-indexer npm package.

not rated 3 2mo ago A tokens not measured

mushi-mushi

1108

kensaurus/mushi-mushi

Skill Claude CodeCodex

Set up, configure, and use Mushi Mushi — the AI-powered QA platform for automatic bug detection, user story mapping, TDD scenario generation, and PDCA auto-improvement. Use when setting up Mushi, configuring SDK/CLI/MCP, managing API keys, or asking how any Mushi feature works.

not rated 3 yesterday A 70 tokens original MIT

ellmos-ai/ellmos-codecommander-mcp

MCP server Claude CodeCodexCursor +2

Developer MCP server: code analysis, JSON repair, imports, diffs, regex, format conversion. Runs locally from the ellmos-codecommander-mcp npm package.

not rated 3 today A tokens not measured original MIT

symbols

1110

p1va/symbols

MCP server Claude CodeCodexCursor +2

MCP server to read, inspect and troubleshoot codebase symbols. Runs locally from the @p1va/symbols npm package. Needs 2 environment variables to run.

not rated 3 1mo ago A tokens not measured original MIT

overllm

1111

theadamdanielsson/overllm

Skill Claude CodeCodex

Find the LLM call you didn't need — your GPT call is a regex. Static, zero-config linter that flags unnecessary GPT/Claude/AI API calls a regex, the stdlib, or a library already does (parsing dates, extracting emails/JSON, sorting, classifying with fixed labels). Runs locally, no model, no API key, nothing phones…

not rated 3 2mo ago A 119 tokens original MIT

lsp-mcp

1112

theUpsider/lsp-mcp

MCP server Claude CodeCodexCursor +2

Universal LSP MCP server. Runs locally from the @theupsider/lsp-mcp npm package.

not rated 3 1mo ago A tokens not measured

codeindex

1113

munhq/codeindex

Plugin Claude Code

Bundles 1 skill, 2 hooks, 1 MCP server · 148 tokens together

Skills that teach any agent to answer code questions structurally instead of reading whole files — symbol lookup, callers, imports and blast radius. Bundles the codeindex MCP server so install wires everything in one step.

not rated 3 changed 4d ago A tokens not measured original MIT

fixgraph-mcp

1114

jawdat6/fixgraph-mcp

MCP server Claude CodeCodexCursor +2

Search 25K+ verified engineering fixes by error or technology. For developers and AI agents. Runs locally from the fixgraph-mcp npm package.

not rated 3 5mo ago A tokens not measured original MIT

audit

1115

justnau1020/claude-os

Skill Claude Code

Orchestrate a full-project consistency audit using a parallel agent team. Spawns lane-specific auditors to cross-reference docs vs code vs tests vs infra, deduplicates findings, and writes a severity-scored audit report.

not rated 3 5mo ago A 46 tokens original Apache-2.0

llm-buster

1116

metravod/llm-buster-skill

Skill Claude CodeCodex

Use this skill when the user asks to audit a codebase for LLM API calls (OpenAI, Anthropic — Python and TS/JS SDKs plus equivalent raw HTTP) and decide which calls can be replaced with deterministic logic. Activates on phrases like 'audit LLM usage', 'bust LLM calls', 'bust the LLM here', 'llm-bust this', 'do I…

not rated 3 3mo ago A 240 tokens original MIT

icode

1117

ayukyo/icode-skill

Skill Claude CodeCodex

A Chinese-language, end-to-end coding workflow with separate steps for planning, review, approval, implementation, checking, and final audit. It also includes optional requirement drafting and log-based cause analysis.

not rated 3 changed today A 157 tokens original MIT

mql5-pro

1118

hushamQA/mql5-pro-skill

Skill Claude CodeCodex

Expert skill for writing, debugging, and optimizing MQL5 code for MetaTrader 5 — Expert Advisors (EAs), custom indicators, scripts, services, libraries, and GUI panels. Use this skill whenever the user mentions MQL5, MQL, MetaTrader 5, MT5, MetaEditor, .mq5/.mqh/.ex5 files, Expert Advisor, EA, trading robot, custom…

not rated 3 2mo ago A 125 tokens

search-mesh

1119

jamestkelly/search-mesh

Plugin Claude Code

Bundles 1 skill · 107 tokens together

Codebase intelligence for coding agents: fast multi-keyword scan, tree-sitter AST probing, context squeezing, and precise patch tools via MCP.

not rated 3 2mo ago A tokens not measured original MIT

jahro-logging

1120

Logiiiii/unity-agent-skills

Skill Claude CodeCodex

Reviews and improves Debug.Log usage in Unity C# projects following structured logging principles: context tags, severity contracts, boundary-based placement, and criticality tiers. Detects common antipatterns (naked Debug.Log, logging in Update, stringly-typed errors), adds missing logs at system/state/error/external…

not rated 3 today A 111 tokens copy · 100% MIT

bug-triage

1121

tinhtran24/maestro

Skill Claude CodeCodex needs its repo

Triage bugs reported in chat/issues, search for duplicates, file or update GitHub issues with full context, and push fix PRs.

not rated 3 1mo ago A 33 tokens original Apache-2.0

dovetail

1122

dbhq-uk/dovetail-skill

Plugin Claude Code

Bundles 1 skill · 102 tokens together

Check whether a repository agrees with itself, for Claude Code and Codex - broken links, dangling heading anchors, orphaned files, duplicate and near-duplicate content, and translations that have fallen behind. Deterministic: no model calls, no network, no dependencies, and it never modifies the repository it scans.…

not rated 3 26d ago A tokens not measured original MIT

nen-conjurer

1124

rlaope/nen

Cursor rule Cursor

Failure-mode-driven reliability engineering — enumerate how it breaks, give every mode a verdict, prove every handler with a reproducing test. Use when the user says "flaky", "harden this before launch", "what if this fails", "error handling", "timeout", "retry", "idempotency", or "race condition"; when an incident or…

not rated 3 1mo ago A 126 tokens original MIT

check-docs

1125

kunalsuri/ai-fication-kit

Skill Claude Code

Kit-maintainer diagnostic (LOCAL-ONLY, not distributed) that audits the README and docs/ for staleness against the repo's real command/skill/CLI roster, stamped tree, and cross-doc consistency. Read-only; produces a severity-ranked findings report.

not rated 3 8d ago A 57 tokens original Apache-2.0

loopcraft

1126

hiphapis/loopcraft

Plugin Claude Code

Bundles 4 skills, 1 agent, 3 hooks · 275 tokens together

Loop engineering for Claude Code — rubric+verifier self-correction, 5-stage memory protocol (fail→investigate→verify→distill→consult), autonomous backlog runner with pluggable sources (file/GitHub/Jira) and write-back.

not rated 3 1mo ago A tokens not measured

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: