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.
MCP server Claude CodeCodexCursor +2
Give AI coding agents access to your Vynix visual feedback, bug reports, and AI diagnosis. Runs locally from the @usevynix/mcp-server npm package. Needs 2 environment variables to run.
Skill Claude Code
Upload source maps to PostHog Error Tracking for Vite.
fengyunzaidushi/claude-code-subagents
Command Claude Code
A debugging command that investigates a specified software problem and attempts to fix it. It uses root-cause analysis, tests possible explanations, and verifies the result.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 167 tokens together
Debug Java programs interactively from the command line via the jdbg CLI: launch a program or attach to a running JVM (JDWP), set breakpoints, step through code, and inspect variables, expressions, threads, and exceptions. Stateful background sessions with structured (text/JSON) output. Cross-platform, native on…
Skill Claude CodeCodex
A cause-and-effect analysis method from modern TRIZ, a problem-solving approach. It repeatedly asks why to trace a visible problem back through the events and conditions that caused it.
Skill Claude CodeCodex
Verifies that a feature is wired through all four layers (schema, API route, runtime, UI) before it may be called complete. Use when adding or auditing any feature — mirrors the connectivity-map method that caught the v1.21 autonomy gap.
firtoz/cf-multiworker-starter-kit
Skill Claude CodeCodex
Fork and template gotchas (env import, routes, typegen, forms, D1, Turbo, HMR, new DO packages). Use when working on apps/web or durable-objects, or when behavior diverges from this stack’s conventions.
Skill Claude CodeCodex
Use when investigating production behavior by querying wide events (a slow route, an error spike, a suspicious deploy, "why is this happening for account X"). Covers the data model, the symptom-to-query workflow, and standing queries worth running.
Skill Claude CodeCodex
An AI-assisted workflow for diagnosing and fixing coding errors, agent problems, and security issues. CyberHuaTuo is the name of the included AI clinic concept.
Skill Claude CodeCodex
A troubleshooting skill for Apache RocketMQ, a messaging system that sends data between applications. It covers failures in sending and receiving messages, message backlogs, connections, and access permissions.
Skill Claude CodeCodex
VCD waveform analysis for RTL debug. Use when the user has a .vcd file and wants to inspect, search, compare, or summarize digital simulation waveforms. Triggers include any mention of VCD files, waveform analysis, signal dump inspection, RTL debug, simulation results, value change dump, or specific VCD signal queries…
Skill Claude CodeCodex
A VM network troubleshooting skill for finding why a virtual machine cannot connect to the network, using KVM commands on its host machine.
MCP server Claude CodeCodexCursor +2
MCP server for GlitchTip error monitoring integration. Runs locally from the glitchtip-mcp npm package.
Cursor rule Cursor
Cursor rule "mcp-debugging" from giantswarm/mcp-prometheus, covering debugging mcp-prometheus via mcp-debug, core debugging tools, debugging workflow, 1. verify all services are running and 2. check mcp server registration.
MCP server Claude CodeCodexCursor +2
Debug probe Model Context Protocol server for AI agents and developer tooling. Runs locally from the dbgprobe-mcp-server Python package. Needs 9 environment variables to run.
Skill Claude CodeCodex
Diagnose and fix Single Step Instrumentation (SSI) issues on Kubernetes — SSI automatically instruments applications for APM without code changes. Only use if the agent and SSI are already configured but traces are missing or instrumentation is not working.
MCP server Claude CodeCodexCursor +2
MCP server "rust-analyzer" as configured in coherentforge/CambiOS. Runs mcp_rust_analyzer with /Users/jasonricca/Library/CloudStorage/OneDrive-Personal/Synthesis/coding/Tooling/mcp-rust-analyzer/.venv/bin/python3. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Model Context Protocol SDK. Runs locally from the mcp Python package.
Skill Claude CodeCodex
Detect silent agent failures and memory degradation. Use when asked for an agent health check, when agent behavior seems off or output quality drops, after long unattended runs, or as part of a scheduled maintenance pass.
MattWenJun/HDD-hypothesis-driven-development
Skill Claude CodeCodex
A hypothesis-driven development method for uncertain coding work such as debugging, optimization, and architecture or configuration changes.
AmolPardeshi99/android-performance-skills
Skill Claude CodeCodex
Exhaustive Android performance skill for writing ANR-free, frozen-frame-free, and janky-free code. Use this skill whenever writing, reviewing, or auditing Android code that involves: coroutines or threading (Dispatchers, withContext, runBlocking, GlobalScope, Mutex, synchronized), Android component lifecycles…
MCP server Claude CodeCodexCursor +2
100% local MCP server for semantic + lexical code search: AST-aware chunking (tree-sitter), hybrid BM25+dense retrieval, optional code knowledge graph. Runs locally from the lynx-mcp Python package.
xinghang-ee-cs/dev-runtime-skill
Skill Codex
A general-purpose code-review and diagnosis workflow written in Chinese, covering controlled fixes, regression checks, requirement checks, audits, and merge readiness.
Skill Claude CodeCodex
Code analysis for TS/JS/Python/C#/Go/Rust/Java/C++/Swift/Kotlin/Zig/Bash — search, impact, refactoring, security, diagnostics.
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: