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.
Skill Claude CodeCodex
Measures and optimizes WebGPU, WebGL and three.js performance in Chrome: low or dropping FPS, janky or stuttering frames, slow render or compute passes, slow WGSL/GLSL shaders, GPU memory leaks (VRAM, buffers, textures). Use to profile a 3D/GPU web page or localhost dev server, find and fix its bottleneck, or prove…
Skill Claude CodeCodex
Use when fixing a bug, defect, issue, or unexpected behavior. Follows Goal-Driven Execution: reproduce with a test, implement the fix, verify no regressions.
Skill Claude CodeCodex
Proactive codebase analysis agent that scans for the highest-impact improvement opportunities across architecture, security, performance, testing, code quality, and more. Use when asked to "look for work", audit a codebase, or find what to fix next.
Agent Claude Code
Active triager — normalizes a raw bug issue into a fix-ready L1 problem or rejects it. First pass on every bug-labeled issue; re-entered on harness kick-back with the failed attempt as evidence. Never fixes, never localizes on first pass.
Skill Claude CodeCodex
A connectivity-checking workflow for Kuaishou internal services, including single sign-on, configuration services, caches, and bastion hosts. A bastion host is a controlled server used to reach protected systems.
Skill Claude CodeCodex
Expose running process manipulation tools (memory read/write, pattern scans, hooks, detours, Lua scripts) inside a 64-bit target process like Star Citizen.
Skill Claude Code
Apply epidemiological reasoning — R0, generation time, susceptibility, contact tracing, herd immunity — to vulnerability propagation, dependency CVEs, credential leaks, bug spread, and incident blast radius.
Plugin Claude Code
Bundles 4 skills · 741 tokens together
Formal modeling and hypothesis-driven debugging using Alloy 6 and Dafny. Includes formal-modeling (write, run, and interpret Alloy 6 or Dafny models for state machines, data invariants, API contracts, permission matrices, and business rules — with reconciliation and enforcement-audit workflow) and formal-debugger…
Vibe-Marketer/plugins-and-skills
Plugin Claude Code
Bundles 9 skills · 539 tokens together
Development skills — create Claude Code extensions (skills, agents, commands, hooks, MCP servers), debug, review code, and generate documents.
Skill Claude Code
Instructions for writing and debugging dsh-hooks-plugin scripts, which run during tool or session events such as before a tool call or after it finishes. These scripts return JSON decisions such as allowing, asking about, or denying an action.
Cursor rule Cursor
Debug and verify backend runtime behavior (HTTP 500s, wrong responses, slow endpoints, suspected N+1 or duplicate queries) by reading the actual recorded request trace via rewynd, instead of guessing from source or adding print statements.
MCP server Claude CodeCodexCursor +2
MCP server "bindiff-mcp" as configured in u21h2/bindiff-mcp. Runs locally from the bindiff-mcp Python package.
j0k3r-dev-rgl/navigation-agent-mcp
Skill Claude CodeCodex
Trigger: MCP navigation, code discovery, symbol lookup, traceflow, tracecallers, endpoints. Use navigation-agent MCP before reading workspace code.
MCP server Claude CodeCodexCursor +2
MCP server for multi-language debugging with AI agents via DAP (Python, Go, Rust, Node.js). Runs locally from the polybugger-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "radare2-mcp" as configured in drvcvt/radare2-mcp. Runs locally from the radare2-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "opengrok-mcp" as configured in SleepyDog053/opengrok-mcp. Runs locally from the opengrok-mcp Python package.
Plugin Claude Code
Bundles 2 skills, 2 commands · 195 tokens together
Authorized iOS static reverse engineering skill for IPA, .app, Mach-O, framework, dylib, and dSYM analysis.
Plugin Claude Code
Bundles 4 skills, 2 agents · 166 tokens together
Control Zen for browsing, web testing, and debugging. Fill forms, capture network and console activity, take screenshots, and inspect console and network activity.
MCP server Claude CodeCodexCursor +2
SSH MCP - tools for remote SSH operations for debugging. Runs locally from the ssh-mcp Python package.
MCP server Claude CodeCodexCursor +2
The XBSL (1C:Element) toolkit: a linter with autofixes, LSP, MCP server, documentation search, project index, metadata scaffolding, translation into English spellings, and a VS Code extension. Runs locally from the xbsl Python package.
Plugin Claude Code
Bundles 2 skills · 246 tokens together
Defense against LLM Rust failure modes: 59 categories of bugs that survive rustc, clippy, and cargo test — async cancellation, unsafe/FFI, concurrency, crypto, supply-chain, tests-that-pass-by-luck, semantic conformance, and systemic performance cost. Ships the rust-intel skill plus /rust-intel:audit, /rust-intel:fix.
Skill Claude CodeCodex
Consult KnownPath for evidence-grounded prior solutions to non-trivial debugging, unfamiliar or recurring technical errors, framework migrations, dependency conflicts, build failures, environment or version mismatches, native configuration problems, and tooling quirks. Use before spending significant time…
MCP server Claude CodeCodexCursor +2
Debug and analyze Nanostores apps with AI: scan stores, monitor runtime events, and search docs. Runs locally from the nanostores-mcp npm package.
Skill Claude Code
Domain skill - inspect Toolbag runtime, GPU, renderer, preferences, materials, and missing texture paths; release unused resources; and control tooltip display through bounded typed operations. Use for TA diagnostics and scene health checks. Not for arbitrary Python execution.
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: