Debugging

17,101 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.

code-intel

1297

vohongtho/code-intel-platform

Cursor rule Cursor

FORBIDDEN: grep, rg, find, cat, sed, ls (for symbol/code discovery) REQUIRED BEFORE ANY CODE ACTION.

not rated 3 3d ago A 2,647 tokens original MIT

pywebview-mcp

1298

com55/pywebview-mcp

Plugin Claude Code

Bundles 1 skill · 89 tokens together

Playwright-style MCP server for pywebview apps — lets Claude see, control, and debug your Python desktop web UI without modifying your app's source code.

not rated 3 2mo ago A tokens not measured

mast

1299

SpikedPunchVictim/mast

MCP server Claude CodeCodexCursor +2

MAST — Monorepo AST Search Tool: semantic code search MCP server and CLI. Runs locally from the @spikedpunch/mast npm package.

not rated 3 19d ago A tokens not measured original MIT

ai-code-graph

1300

sakrut/ai-code-graph

Cursor rule Cursor

AI Code Graph MCP workflow for C# analysis and edits.

not rated 3 7mo ago A 213 tokens original MIT

cartograph

1301

adder-factory/cartograph

Skill Claude CodeCodex

Explore a codebase through Cartograph v2's native RocksDB code graph: intent-aware context, exact/BM25/hybrid search, callers/callees/impact, affected tests, live source, review, freshness, and bounded index administration.

not rated 3 changed 18d ago A 0 tokens original MIT

code-explorer

1302

phuetz/code-explorer

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 40 tokens together

Graph-powered code intelligence for AI agents: a pre-indexed knowledge graph of your whole codebase (symbols, callers, impact/blast radius, hotspots, complexity) served over MCP. Ships the code-explorer skill and the code-explorer MCP server. Requires the code-explorer binary on PATH and an index (code-explorer analyz.

not rated 3 15d ago A tokens not measured

graphify

1303

real-limitless/ansible-flow-mcp

Cursor rule Cursor

This project has a graphify knowledge graph at graphify-out/.

not rated 3 2d ago A 294 tokens copy · 100% Apache-2.0

claimidx

1304

claimidx/claimidx

Skill Claude Code

Query and contribute to Claimidx before retrying a failure. Claimidx is prior art for agents — a claim index of errors other agents already paid to solve. Use when debugging, hitting a known error, retrying the same stack, burning tokens on a ModuleNotFoundError or TypeError, or after you learn a fix. Never leave a…

not rated 3 changed 13d ago B 103 tokens original Apache-2.0

satori

1305

ham-zax/satori

Skill Claude CodeCodex

Satori MCP workflow for repository code intelligence: finding where unfamiliar behavior lives, tracing ownership and callers, reviewing change impact, and handling index readiness (create, sync, reindex, cancel). Use when a task needs Satori search, navigation, or index lifecycle decisions beyond a known path or…

not rated 3 changed 16d ago A 63 tokens AGPL-3.0

debugar-advpl

1306

Guipegoraro/tds-mcp

Skill Claude CodeCodex

Depurar ou executar rotina AdvPL/TLPP no AppServer pelo MCP tds (tdsdebug, tdsrun). Use para depurar (breakpoint, valor de variável em execução), rodar/testar uma User Function ou relatório no servidor, ou reproduzir erro de execução (error.log).

not rated 3 changed 15d ago A 69 tokens original MIT

topprismdata/agent-nurture-framework

Skill Claude CodeCodex

Python buffers stdout and stderr when output is not connected to a terminal (TTY). This causes log files to appear empty even though the process is running and producing output. Use when: (1) Background script log file is empty but process is running (visible in ps), (2) Redirecting Python script output to a file and…

not rated 3 24d ago A 153 tokens original MIT

funcfinder

1309

ruslano69/funcfinder

Skill Claude CodeCodex

Map repositories, locate and extract functions/types, trace calls and dependencies, and edit Go/Rust/C#/D/JS/TS/Kotlin/Goose declarations through versioned JSON code objects. Use for code navigation, impact analysis and function/type replacement with the funcfinder toolkit.

not rated 3 changed 14d ago A 59 tokens original MIT

ast-graph-traceability

1310

davenportjw/agent-skills

Skill Claude CodeCodex

Queries and maintains the multi-repo, tamper-proof AST & Cross-Layer Lineage GraphDB ( /.ast-graph/ast.db, SCIP + SQLite LPG) across TypeScript/JavaScript, Python, Go/Templ, Rust, Terraform/HCL, SQL, Dockerfile, Protobuf, GraphQL, Java, Kotlin, C#, Ruby, Elixir, PHP, C/C++, Swift, Zig, and WebAssembly/WIT…

not rated 3 changed 8d ago B 144 tokens original Apache-2.0

visor-context

1311

dibun75/visor

Skill Claude CodeCodex

Use V.I.S.O.R. to obtain focused, verified repository context before code exploration, debugging, refactoring, or dependency-impact work. Do not use for unrelated general questions.

not rated 3 3d ago A 39 tokens original MIT

runx

1312

bittencourtthulio/expxdev

Skill Claude Code needs its repo

Use ao relatar defeito em sistema que já existe: não funciona como deveria, não segue o padrão esperado, trava, some ou dá valor errado — mesmo sem a palavra bug. Inclui falha de interface e interação (arrastar, clicar, salvar) e ajuste de tela, cálculo ou campo. Feature nova é sprintx.

not rated 3 1mo ago A 71 tokens original MIT

loopcraft

1313

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 2 3mo ago A tokens not measured

viewdoctor

1314

KamnevVladimir/ViewDoctor

Skill Claude CodeCodex

Run deterministic SwiftUI and multi-module analysis after editing Swift code, before review, or when an AI-generated change may have introduced performance, task-lifetime, or module-boundary risks.

not rated 2 2mo ago A 40 tokens original MIT

source-map-parser-mcp

1315

MasonChow/source-map-parser-mcp

MCP server Claude CodeCodexCursor +2

Parse JavaScript error stack traces back to original source code using source maps. Runs locally from the source-map-parser-mcp npm package. Needs 2 environment variables to run.

not rated 2 1y ago A tokens not measured original MIT

forensic-deepdive

1316

Dhevenddra/forensic-deepdive

Plugin Claude Code

Bundles 3 skills, 1 MCP server · 339 tokens together

Persistent code knowledge graph + 9 composite MCP tools (impact, context, archaeology, flow, query, recordinsight, recallinsights, visualize, trace) for AI coding agents.

not rated 2 2mo ago A tokens not measured original Apache-2.0

ohm-mcp

1317

Murugarajr/ohm-mcp

MCP server Claude CodeCodexCursor +2

AST-based Python refactoring MCP server with safe automated refactorings and rollback. Runs locally from the ohm-mcp npm package.

not rated 2 9mo ago A tokens not measured original MIT

graphlens-navigation

1318

Neko1313/graphlens-mcp

Skill Claude Code

Navigate the code graph using graphlens MCP tools instead of reading files or grepping. Use when asked: "what calls X", "what breaks if I change X", "who uses this function", "what does this function depend on", "impact analysis", "find callers", "find references", "what implements/extends X", "what's in this file"…

not rated 2 3mo ago A 147 tokens original MIT

sentinal-redis

1319

Musaraf-M/sentinal

Skill Claude Code

Monitor Redis server health, memory, performance, and BullMQ queues. Check queue depths, inspect failed jobs, analyze slow queries, and diagnose issues.

not rated 2 6mo ago A 35 tokens original MIT

statecli

1320

statecli/mcp-server

MCP server Claude CodeCodexCursor +2

State replay and self-debugging for AI agents. Track, replay, undo, checkpoint. Runs locally from the statecli-mcp-server npm package.

not rated 2 7mo ago A tokens not measured 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: