Debugging

16,959 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.

cypress-debugger

49

kiali/kiali

MCP server Claude CodeCodexCursor +2

MCP server "cypress-debugger", hosted remotely at 127.0.0.1, as configured in kiali/kiali.

not rated 3.6k +1 yesterday A tokens not measured original Apache-2.0

five-whys

50

wesammustafa/Claude-Code-Everything-You-Need-to-Know

Skill Claude Code

Finds the root cause of a bug, failure or recurring problem by asking "why" until the answer is a cause you can fix. Use when the user asks why something keeps happening, or wants the root cause rather than a quick fix.

not rated 3.5k +38 3d ago A 53 tokens original

NVIDIA-NeMo/Switchyard

Skill Claude Code needs its repo

Deep dive on Harbor trial results for tasks that use SWE-Bench-style F2P (FAILTOPASS) and P2P (PASSTOPASS) reference tests. Diagnoses why an agent failed and audits whether a failing task is genuinely hard or unfair (instruction-vs-verifier mismatch). Use when the user asks to analyze, debug, investigate, or deep dive…

not rated 3.5k +24 today A SkillSpector: warn 238 tokens original Apache-2.0

xpf0000/FlyEnv

Skill Claude CodeCodex

Use when implementing or reviewing FlyEnv multi-step operations, batch actions, PID candidate filtering, cleanup, supplementary actions, or changes to throw/reject and terminal result handling.

not rated 3.3k +18 yesterday A 41 tokens original BSD-3-Clause

graphjin-eval

54

dosco/graphjin

Skill Claude CodeCodex

Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.

not rated 3.2k +9 changed 2mo ago A SkillSpector: pass 27 tokens original Apache-2.0

antfu/node-modules-inspector

Skill Claude CodeCodex

Inspects a project's installed nodemodules and produces three reports: duplicated packages (installed in multiple versions), packages sorted by install size, and maintenance actions (dep-upgrade opportunities + publint findings, grouped by consumer/author). Use when the user wants to audit dependencies, find duplicate…

not rated 3.0k +2 1mo ago A SkillSpector: warn 156 tokens original MIT

gonzo

57

control-theory/gonzo

Plugin Claude Code

Bundles 1 skill · 49 tokens together

Set up and use Gonzo, the open-source terminal log analysis tool. Detects deployment platforms (Vercel, Supabase, K8s, Docker, AWS, Cloudflare, Fly, Render, Railway, Netlify), generates the right pipe command with platform-specific normalizers, and configures AI analysis. Use when the user wants to tail, watch, stream.

not rated 2.8k +2 1mo ago A tokens not measured original MIT

rev-idapython

59

P4nda0s/reverse-skills

Skill Claude CodeCodex

IDAPython and IDALib script reference for reverse engineering. Activate when the user needs to write IDAPython scripts in IDA, use IDALib for headless analysis, operate on IDB databases, debug with IDA, manipulate memory/registers, traverse functions/blocks/instructions, work with Hex-Rays decompiler API, handle…

not rated 2.3k +13 6mo ago A Socket: passSnyk: pass 84 tokens

prp-core

60

Wirasm/prp

Plugin Claude Code

Bundles 1 hook

Complete PRP workflow automation as agent skills - prd, plan, issue delivery, implement, debug, commit, pr, review, codebase research, a detached build loop, and a skill-authoring meta-skill, with specialized agents.

not rated 2.3k +1 1mo ago A tokens not measured original MIT

jshookmcp

61

vmoranv/jshookmcp

MCP server Claude CodeCodexCursor +2

Search-first MCP server for JavaScript reverse engineering: 735 tools across 36 domains. Runs locally from the @jshookmcp/jshook npm package.

not rated 2.1k +11 yesterday A tokens not measured AGPL-3.0

formal-stop-retry

62

coder/xum

Skill Claude CodeCodex

Model-check (TLA+ with TLC) that a Stop ends the stream auto-retry loop, so no automatic retry starts a stopped workspace's turn again. Use when a change touches RetryManager, AgentSession's auto-retry or stream-error handling (handleStreamError, handleStreamFailureForAutoRetry, retryActiveStream, resumeStream), a…

not rated 2.1k +7 today A 145 tokens AGPL-3.0

monoscope-tech/monoscope

Skill Claude CodeCodex

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

not rated 2.0k +26 yesterday A 21 tokens AGPL-3.0

Sentry

64

reactnativecn/react-native-update

MCP server Claude CodeCodexCursor +2

Sentry's hosted MCP server: lets the agent search and read issues, errors and traces. Remote server at mcp.sentry.dev.

not rated 2.0k +1 2d ago A tokens not measured

test-writer-fixer

65

composio-community/awesome-claude-plugins

Plugin Claude Code

Bundles 1 agent · 0 tokens together

Use this agent when code changes have been made and you need to write new tests, run existing tests, analyze failures, and fix them while maintaining test integrity. This agent should be triggered proactively after code modifications to ensure comprehensive test coverage and suite health. Examples:\n\n \nContex.

not rated 2.0k +9 yesterday A tokens not measured

zhnt/loushang

Skill Claude CodeCodex

Repair the fixed integer calculator using current failure evidence.

not rated 2.0k +58 yesterday A 16 tokens original Apache-2.0

pawurb/hotpath-rs

Skill Claude Code

Build a Grafana dashboard JSON for a Rust project profiled with hotpath. Writes the dashboard file with context-aware panels (SQL and HTTP time per route, N+1 detection, memory and time per request, channel queues, lock contention, Tokio workers, per-thread CPU and allocations, profiling overhead) limited to what the…

not rated 1.9k changed 26d ago A 109 tokens original MIT

mex-statechart

68

mex-memory/mex

Skill Codex

Explain complicated existing behavior using checked state diagrams. Use when asked for a state diagram, to diagram the previous explanation, show a bug or recovery path, compare a proposed fix or existing TLA+ spec, or derive a model from an agreed chart. Generates native Mermaid and a readable terminal fallback…

not rated 1.8k +9 2d ago A 73 tokens original MIT

tw

69

tracewayapp/traceway

Plugin Claude Code

Bundles 4 skills, 1 plugin · 472 tokens together

Traceway skills: /tw:traceway debugs production issues through the traceway CLI, /tw:traceway-learn is the full guide to every part of Traceway, /tw:traceway-setup instruments a project to report to a Traceway instance.

not rated 1.8k +6 changed 21d ago A tokens not measured original MIT

art-of-debugging

70

stas00/the-art-of-debugging

Skill Claude CodeCodex

Systematic methodology and concrete tool recipes for debugging Unix, Python, and PyTorch programs - crashes, hangs, segfaults, wrong output, CUDA OOM, NaN/Inf, slowness, and multi-node/multi-GPU issues. Use when a program crashes, hangs, deadlocks, segfaults, runs out of memory (OOM), produces NaN/Inf or wrong…

not rated 1.7k +2 changed 23d ago B 193 tokens CC-BY-SA-4.0

burrow-system-tools

71

caezium/burrow

Skill Claude CodeCodex

Diagnose and fix the user's Mac with Burrow's local MCP tools (burrowdoctor, burrowsnapshot, burrowtopprocesses, burrowprocessusage, burrowports, burrowanalyze, burrowdiskforecast, burrowdupes, burrowanomalies, burrowagentaudit, burrowclean, …). Use whenever the Mac is slow, hot, loud, low on disk, draining battery…

not rated 1.7k +91 yesterday A SkillSpector: pass 194 tokens original MIT

crash-analyst

72

svnscha/mcp-windbg

Agent Claude Code

Deep-dive a Windows crash dump and return a written verdict. Use when a dump needs more than a first look - several hypotheses to rule out, many frames or threads to walk, or a conclusion someone will act on. Give it the dump path and the question.

not rated 1.7k +19 changed 1mo ago A 60 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: