Debugging

23,803 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.

fix-bug

193

justxor/Harness_ru

Command Claude Code

A command for fixing a defect described by the user or identified by a ticket number, within the current module's boundaries.

not rated 210 +7 20d ago A 24 tokens

sentry-agent

194

modem-dev/baudbot

Skill Claude CodeCodex

Sentry monitoring agent — watches.

not rated 209 3mo ago A 10 tokens original MIT

symdex-code-search

195

husnainpk/SymDex

Skill Claude CodeCodex

This skill should be used when finding, tracing, or understanding code in a repository with SymDex available. Trigger it for requests like "where is this defined?", "who calls this?", "what route handles this path?", "show me the file outline", "search this codebase by intent", or any task that would otherwise rely on…

not rated 209 4mo ago A 85 tokens original MIT

graphmind

196

aouicher/graphmind

Skill Claude CodeCodex

Before using Grep, find, rg, ag, or reading files to understand code: You MUST query graphmind first. Only fall back to grep/find if graphmind cannot answer (e.g., string literals, config values, non-code patterns).

not rated 207 +1 1mo ago A 43 tokens original MIT

nemesis-auditor

197

NeverSight/learn-skills.dev

Skill Claude CodeCodex

The Inescapable Auditor. Runs the full Feynman Auditor (Stage 1) and full State Inconsistency Auditor (Stage 2) as primary steps, then fuses their outputs in a feedback loop (Stage 3) to find bugs at the intersection that neither alone would catch. Language-agnostic. Triggers on /nemesis or nemesis audit.

not rated 207 yesterday A 83 tokens

debug

198

chsami/Microbot

Skill Claude CodeCodex

Autonomously debug the Microbot client/engine (pathfinder, walker, widgets, cache layer, agent server, etc.) from a free-text bug description. Starts the client, reproduces the bug via hot-reloaded probe plugins, edits engine source, rebuilds, and verifies the fix — all without human intervention. Use when the user…

not rated 206 +1 6d ago A 100 tokens original BSD-2-Clause

ghidra-cli

199

akiselev/ghidra-cli

Skill Claude CodeCodex

Use ghidra-cli for reverse engineering tasks: binary analysis, decompilation, function inspection, cross-reference analysis, pattern discovery, binary patching, and type system management. Activate when the user requests: - Binary analysis or reverse engineering - Decompilation or disassembly - Function listing…

not rated 205 +3 27d ago A 132 tokens GPL-3.0

nplog

200

NotePlan/plugins

Skill Claude CodeCodex

Read NotePlan's plugin log to debug a plugin. Use when investigating why a NotePlan plugin misbehaved, after triggering a plugin command or x-callback URL, when the user says a plugin "isn't working"/"threw an error"/"did nothing", or when you need to see what a plugin logged. Wraps scripts/nplog/nplog --json, which…

not rated 204 5d ago A 109 tokens original MIT

dariushoule/x64dbg-skills

Instructions file

Instructions for dariushoule/x64dbg-skills, covering x64dbg-skills, structure, skills, key patterns and dependencies.

not rated 204 5mo ago A 503 tokens original MIT

lighthouse-mcp

202

priyankark/lighthouse-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Google Lighthouse performance metrics. Runs locally from the lighthouse-mcp npm package.

not rated 203 +1 3mo ago A tokens not measured original MIT

renderdoc-gpu-debug

203

rudybear/renderdoc-skill

Skill Claude CodeCodex

GPU frame debugging with RenderDoc via rdc-cli. Use this skill when the user mentions: GPU debugging, .rdc files, RenderDoc, shader issues, pipeline state, rendering artifacts, frame capture, shadow problems, visual glitches, draw calls, render targets, pixel history, texture inspection, depth buffer, blend state…

not rated 202 6mo ago A 200 tokens original MIT

index-analyzer

204

ericbuess/claude-code-project-index

Agent

MUST BE USED when analyzing PROJECTINDEX.json to identify relevant code sections. Provides deep code intelligence through ultrathinking analysis of codebase structure, dependencies, and relationships.

not rated 196 11mo ago A 38 tokens original MIT

apkmcp-auto

205

kggzs/ApkMCP-Auto

Skill Claude CodeCodex

An automation toolkit for examining Android APK files, which are installable Android app packages.

not rated 196 +4 4mo ago A 70 tokens

backnotprop/pstack

Skill Claude CodeCodex

Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.

not rated 193 +28 16d ago A 48 tokens original MIT

issue-stack-tracer

208

VishalJ99/claude-docker

Agent Claude Code

Use this agent when you need to diagnose user-reported issues by mapping out the complete technical execution path. This agent excels at transforming vague problem descriptions like 'button doesn't work' into comprehensive technical blueprints that reveal exactly where implementations fail. Perfect for debugging…

not rated 188 7mo ago A 377 tokens original MIT

clojure-eval

209

bhauman/clojure-mcp-light

Skill Claude CodeCodex

Evaluate Clojure code via nREPL using clj-nrepl-eval. Use this when you need to test code, check if edited files compile, verify function behavior, or interact with a running REPL session.

not rated 188 2mo ago A 52 tokens EPL-2.0

reclaim-code-entropy

210

Yevanchen/reclaim-code-entropy

Skill Claude CodeCodex

Find, rank, and safely remove accidental codebase complexity by proving real consumers, dynamic entrypoints, compatibility obligations, duplicate representations, speculative surfaces, and lifecycle ownership. Use when asked to simplify or clean up a repository, reclaim code entropy, reduce over-engineering or…

not rated 183 +1 14d ago A 148 tokens original MIT

vpn-troubleshoot

211

Sergei-thinker/vpn-setup

Skill Claude CodeCodex

VPN troubleshooting decision tree. Use when user reports VPN problems: 'VPN not working', 'can't connect', 'stopped working', 'no internet through VPN', 'slow VPN', 'troubleshoot'. Also use when deployment fails.

not rated 179 +1 4mo ago A 52 tokens original MIT

systing-analyze

212

josefbacik/systing

Skill Claude CodeCodex

Analyze a systing trace database (.duckdb). Use when the user asks about a systing trace — flamegraphs, scheduling latency, CPU hotspots, network behavior, memory/allocation activity, off-CPU time, TPU op/metric data, or any question about what's in a trace.duckdb file. Orchestrates the systing-analyze MCP tools…

not rated 175 7d ago A 100 tokens original MIT

tendril-debug-plan

213

Ivy-Interactive/Ivy-Tendril

Skill Claude CodeCodex

Debug a Tendril plan by analyzing its execution logs, session JSONL, verification results, and checking infrastructure. Produces actionable bugfix and improvement recommendations. Use when the user wants to investigate why a plan failed, behaved unexpectedly, or to audit plan execution quality.

not rated 174 7d ago A 59 tokens

test-fixer

214

mitchdenny/hex1b

Skill Claude CodeCodex

Agent for diagnosing and fixing flaky terminal UI tests in the Hex1b test suite. Use when tests pass locally but fail in CI, or when tests exhibit timing-sensitive behavior.

not rated 173 6d ago A 39 tokens original MIT

embedded-debugger

215

Adancurusul/embedded-debugger-mcp

Plugin Claude Code

Bundles 1 skill · 75 tokens together

Embedded debugger workflow for probe-rs targets. Provides a CLI-first skill and optional MCP server for probe discovery, target checks, flashing, memory access, and RTT workflows.

not rated 171 +2 1mo 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: