15,552 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.
Plugin Claude Code
Bundles 1 skill, 1 agent, 2 hooks · 134 tokens together
Transparent indexed code search that automatically accelerates Grep on large codebases using qgrep indexes.
Cursor rule Cursor
Logging in this project should be detailed, scoped, and extensive. Logs are the primary way to debug test runs, so they should make execution history obvious.
MCP server Claude CodeCodexCursor +2
Rust Minidump MCP server. Runs locally from the rust-minidump-mcp Python package.
Cursor rule Cursor
Your task is to help users to write ast-grep rules to search code. User will query you by natural language, and you will write ast-grep rules to search code.
Skill Codex
Audit and harden the brain-mcp repository with Hermes Agent. Use when Codex needs to inspect this repo for reliability, orchestration, or maintainability weak spots; run a read-only Hermes audit; implement one or two bounded fixes locally; validate the result; and then commit and push only the intended changes.
MCP server Claude CodeCodexCursor +2
A locally run tool for reading and interpreting log files. Logs are records of events and errors produced by software.
Skill Claude CodeCodex
Use httap to inspect, filter, and intercept HTTP traffic. Activate when httap MCP tools are available or when the user mentions HTTP traffic, API debugging, request interception, or mocking.
Skill Claude Code
Skill "openocd-mcp-debug" from luiox/openocd-mcp, covering openocd-mcp embedded debug skill, project overview, core architecture, mcp tool complete reference and project & configuration.
MCP server Claude CodeCodexCursor +2
Modern TypeScript MCP server for AI-powered code search and querying with Greptile API. Runs locally from the greptile-mcp-server npm package.
shanraisshan/draw-json-architecture-skill
Skill Claude Code
Draws an interactive HTML Architecture Viewer for any code flow the user names. Walks through seven research-driven steps (flow, name, repo research, lens colors, evidence flags, lens+mechanism per stop, build) and verifies links, claims, and generated artifacts before delivery.
DEFRA/claude-legacy-reveng-plugin
Plugin Claude Code
Bundles 3 skills, 8 agents · 455 tokens together
Claude Code plugin for Defra's Legacy Application Programme (LAP) to aid in reverse engineering legacy applications.
MCP server Claude CodeCodexCursor +2
MCP server "debugforge" as configured in YangPan2020/debugforge. Runs locally from the debugforge Python package.
Skill Claude CodeCodex
Reference for designing, changing, debugging, testing, and releasing AI-generated code so failures become durable regression assets and completion is proven across the real delivery boundary.
Plugin Claude Code
Bundles 1 skill, 3 commands · 108 tokens together
Static technical-debt analysis across 14 languages, exposed as MCP tools and resources (SQALE ratings, debt summaries, custom rules, dependency vulnerabilities).
Skill Claude CodeCodex
Định vị dòng trước khi đọc file hoặc tìm file trong cây thư mục — tránh đọc mù, tiết kiệm token. Dùng khi cần tìm hàm, class, symbol, hoặc bất kỳ pattern nào trong source code trước khi gọi viewrange. Hai công cụ: findtree.py (tìm file nào có chứa pattern) và findtool.py (tìm dòng nào trong một file).
MCP server Claude CodeCodexCursor +2
BugHerd API v2 integration — 37 tools for projects, tasks, comments, and webhooks. Runs locally from the bugherd-mcp npm package. Needs 1 environment variable to run.
Plugin Claude Code
Bundles 8 skills, 10 commands, 2 hooks · 613 tokens together
Zero-config, token-efficient code exploration for any language. Auto-indexes your codebase and keeps the index fresh — just search, fetch, or explore. Uses LSP for precision when available, falls back to ctags, then ripgrep. Up to 99% fewer tokens than reading full files.
troycheng/cuda-kernel-optimizer
Skill Codex
Use when optimizing or diagnosing GPU workload performance with CUDA, CUTLASS, Triton, PyTorch, vLLM or TensorRT-LLM; interpreting NCU, Nsys or PyTorch Profiler evidence; or preparing the workload and correctness checks for such optimization. General coding, skill maintenance and conceptual GPU questions do not…
Skill Claude CodeCodex
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
Plugin Claude Code
Bundles 5 skills, 6 agents · 487 tokens together
Codebase health tools: deep audits via orchestrated specialists (security, performance, libraries, quality, dead code) plus dead-code cleanup and documentation maintenance.
Skill Codex
Audit, score, remediate, and verify repositories across code hygiene, architecture hygiene, and engineering hygiene. Use for an explicit Rigor3 or three-hygiene request, a strict repository-wide quality audit, a cross-dimensional cleanup plan, or before-and-after verification. Do not use for an ordinary focused review…
Skill Claude CodeCodex
Use to orient in an unfamiliar codebase with graphify, a local tree-sitter code graph — "what does this symbol touch", "how do these two connect", "trace this call chain". Opt-in (the human installs graphify once). A forward-orientation aid, NOT a reliable reverse-dependency tool. Shipped and kept current by Loom.
Plugin Claude Code
Bundles 1 skill · 67 tokens together
Let your AI coding agent debug what already happened in your real browser. peek records masked rrweb sessions of your real browser to a local store and exposes them (DOM history, console/network errors, the action before an error, session-to-Playwright repro) to coding agents over MCP — and, with per-origin consent…
Plugin Claude Code
Bundles 1 skill · 213 tokens together
Architectural health for Python codebases: trended score, cycle detection, layer rules, blast radius, CI test selection. Exposes 13 MCP tools and bundles the archy skill so Claude can run the snapshot/impact/edit/diff loop without manual prompting.
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: