COMPETITOR MONITORING FOR PLUGIN DEVELOPERS
Claude plugin directory
Follow your plugin and competitors. Review changes to their positioning, capabilities and published terms, with dated source evidence.
Explore 2,729 plugins across 15 categories.
Selected:shell ×
Follow up to 3 plugins for free across Codex and Claude. Newest means first added to our catalog, not the publisher’s release date.
All plugins 36
1–36 of 36| Plugin / developer | Category | Follow |
|---|---|---|
xilinx-suiteQingquanYaoAn AI coding skill (Claude Code / Codex / OpenClaw) that turns natural language into production-ready Vivado / Vitis HLS / Vitis Unified ... |
UncategorizedVersion 1.0.0 | View details → |
using-cmuxhummer98A Claude Code plugin that teaches the agent to operate cmux, a terminal multiplexer with first-class agent integration. Provides skill pa... |
UncategorizedVersion 1.8.0 | View details → |
upkeepKyleNesiummacOS cleanup and update assistant for Claude Code.
Scans your Mac for reclaimable disk space, leftover app data, stale caches, broken La... |
UncategorizedVersion 1.8.1 | View details → |
trampMarc FargasTRAMP-like transparent remote execution for AI coding agents. Routes file and shell operations (bash, read, write, edit, glob, grep, ls) ... |
UncategorizedVersion 0.1.0 | View details → |
skill-security-checkaliksSecurity audit plugin that scans Claude Code skills, hooks, and MCP configurations for threats. Detects 37 attack patterns including prom... |
UncategorizedVersion 2.5.0 | View details → |
skill-safety-auditorMatthew MillerSkill Safety Auditor is a Claude Code skill that audits third-party skills for security risks before or after you install them. It runs 1... |
UncategorizedVersion 1.1.0 | View details → |
security-watchdogDeveloper not provided> Automatic security scanner for Claude Code plugins — detects new or updated extensions at session start and scans them for prompt injec... |
UncategorizedVersion not provided | View details → |
railguardrailguard-devRailguard is a safer, context-aware alternative to --dangerously-skip-permissions for Claude Code.
Instead of choosing between approving... |
UncategorizedVersion 0.5.1 | View details → |
pty-mcpraychao-oaoInteractive PTY sessions for AI agents. Supports local shell, SSH, serial port, and persistent remote sessions via MCP. Enables AI agents... |
UncategorizedVersion 0.11.2 | View details → |
prompt-sentinel-v1Developer not providedProtect Claude Code workflows with Prompt_Sentinel. Use when a task involves sensitive shell, file, write, export, approval-gated, or ins... |
UncategorizedVersion not provided | View details → |
preserve-sessionDeveloper not providedPreserves Claude Code session history across project directory renames, moves, and copies by assigning each project a path-independent UU... |
UncategorizedVersion not provided | View details → |
openregistrySophymarineLive, government-identical company data from 27 national registries in one install — MCP server + 10 Skills + 6 slash commands. Walk cros... |
UncategorizedVersion 1.0.0 | View details → |
notify-soundsAxGordPlays system sounds in Claude Code when a task finishes or when permission is needed, so you don't have to keep watching the terminal. Cr... |
UncategorizedVersion 0.1.4 | View details → |
model-advisorJason BoyleClaude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface. |
DevelopmentVersion 1.0.1 | View details → |
mo-es-governance-for-coworkEllo Cello LLCConstitutional AI governance for Claude Cowork — no shell dependencies, prompt-native enforcement. Set behavioral modes (High Security, H... |
UncategorizedVersion 1.0.0 | View details → |
magicianAlexander TyagunovComprehensive software development lifecycle plugin that takes task from the idea to merged PR autonomously. Core capabilities:
1. Dynam... |
UncategorizedVersion 2.0.1 | View details → |
infiniteclaudDouglas KazunariAutonomous automation agent for Claude Code with 20 specialized MCP tools (Playwright web control, filesystem, macOS native via PyAutoGUI... |
UncategorizedVersion 1.0.0 | View details → |
hsFrancesco Marinoni MorettoPre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-clo... |
UncategorizedVersion 1.4.9 | View details → |
harnesskitice-ice-bearAdaptive harness for vibe coders — automatically detects your repo stack, applies experience-level guardrails (beginner/intermediate/adva... |
UncategorizedVersion 0.4.3 | View details → |
guardTracineHQ contributorsPreToolUse hooks for Claude Code that deny dangerous shell, git, and credential commands before they run: `rm -rf /` shapes, `git push --... |
UncategorizedVersion 1.5.0 | View details → |
get-design-donehegemonartAgent-orchestrated design pipeline for Claude Code. Five stages (brief → discover → plan → design → verify), 33 specialized agents, 12 to... |
UncategorizedVersion 1.14.5 | View details → |
deeplake-hivemindActiveloopCloud-backed persistent memory for Claude Code powered by Deeplake. Automatically captures all session activity: user prompts, assistant ... |
UncategorizedVersion 0.7.145 | View details → |
ddwInalpsA development harness for Claude Code that enforces disciplined workflows — decisions before code, tasks before implementation. Includes ... |
UncategorizedVersion 1.0.0 | View details → |
copilot-bridgeMavromatisKMCP bridge that lets Claude Code delegate coding tasks to GitHub Copilot CLI. Forwards prompts to the locally installed
Copilot CLI and r... |
UncategorizedVersion 1.0.0 | View details → |
clawkeeperRAD SecurityFrictionless security, compliance, and threat detection for Claude Code and Co-Work. Advanced Behavioral detection patterns catch credent... |
UncategorizedVersion 1.1.2 | View details → |
claudecode-rexd-targetSamir AlibabicClaude Code plugin for working with configured remote machines through REXD over SSH stdio. It adds target switching, remote filesystem t... |
UncategorizedVersion 0.1.4 | View details → |
claude-voice-cueDeveloper not providedSpeaks "Input needed" the instant Claude Code is waiting on you — tool approval, plan review, or any attention-wanted prompt. Sub-100ms r... |
UncategorizedVersion not provided | View details → |
claude-prompt-libraryFrancisco MastromarinoSave, search, load and manage reusable prompts across projects. Build a personal prompt library that persists across sessions and works i... |
UncategorizedVersion 1.0.0 | View details → |
claude-mac-chromePedro Henrique Souza BalbinoProfessional Chrome automation for Claude Code on macOS. Deterministic multi-profile detection via Chrome's authoritative Local State cat... |
UncategorizedVersion 1.1.1 | View details → |
ccguardsoyukkeSecurity guard hook for Claude Code. Evaluates every tool call (Bash, Edit, Write, Read, MCP) against 864 pattern-matching rules to block... |
UncategorizedVersion 0.5.0 | View details → |
ccbeepTheGreatCBHSound notifications for Claude Code. Plays distinct system sounds when tasks complete or fail, so you don't need to watch the terminal. Z... |
UncategorizedVersion 1.0.0 | View details → |
auto-approve-compound-bashOry BandAuto-approve compound Bash commands (pipes, chains, subshells) by parsing each segment via shfmt AST and checking against allow/deny lists |
UncategorizedVersion 1.0.0 | View details → |
| UncategorizedVersion not provided | View details → | |
| UncategorizedVersion 0.1.0 | View details → | |
Preset CLI SkillsPresetPreset CLI skills for explicit shell, scripting, and CI/CD workflows driven by the `sup` CLI (PyPI package `superset-sup`). Use only for ... |
DevelopmentVersion 0.5.0 | View details → |
Desktop CommanderDesktop CommanderMCP server for terminal commands, process management, and file operations across text, code, PDF, DOCX, Excel, images, and structured data. |
ProductivityVersion 0.2.0 | View details → |
Sources and coverage
Last checked: Nov 7, 2026 · 06:00 UTC. Refreshed every 6 hours.
We collect the Claude Marketplace and Anthropic-hosted catalogs:
Matching repository entries are combined; unrelated plugins with the same name stay separate. Source labels do not imply an Anthropic verification badge. Reported installs are source-reported counts, not independently verified users or revenue. Missing counts mean unknown.
We archive listing and manifest snapshots. Linked plugin code is not downloaded or executed.
Catalog results: live query. Your account and Follow status are live.