clash
Permission enforcement for Claude Code tool usage with policy-based rules, hierarchical settings, and optional kernel-enforced sandboxing via Landlock/seccomp (Linux) and Seatbelt…
Plugin-Paket · von Empathic
Überblick
clash ist ein Plugin-Paket für KI-Coding-Tools von Empathic. Marktplätze, die wir lesen und die es listen: 1 (Community GitHub marketplaces). Wir haben es erstmals am 2026-10-17 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-21.
Permission enforcement for Claude Code tool usage with policy-based rules, hierarchical settings, and optional kernel-enforced sandboxing via Landlock/seccomp (Linux) and Seatbelt (macOS)
Was es abfragt
- Wird als Plugin-Paket installiert
- Deklarierte Hooks: 5
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als Claude-Code-Plugin
Erstellt aus den Angaben von Community GitHub marketplaces.
/plugin marketplace add empathic/clash
/plugin install clash@clashWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Community-Marktplatz empathic/clash (Quelle auf GitHub öffnen) | Gelistet | 0.1.0 | Forks (GitHub): 6 Sterne (GitHub): 34 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
In einem Community-Marktplatz gelistet
| Marktplatz | Repository | Sterne (GitHub) |
|---|---|---|
| clash | empathic/clash | 34 |
Was das Paket enthält
So veröffentlicht auf Community GitHub marketplaces.
Hooks: 5
NotificationPermissionRequestPostToolUsePreToolUseSessionStart
Was sich geändert hat
- Wird seitdem als Produkt geführt
- Community GitHub marketplaces: erschienen
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
macOS security hardening for Claude Code — PreToolUse/PostToolUse hooks that block secret exfiltration, prompt injection, persistence, and self-tampering.
-
Intent-based security enforcement for Claude Code. ArmorClaude makes Claude declare what it intends to do before doing it, then checks every tool call against that plan. Adds…
-
Balanced default runtime security plugin for Claude Code with shell, git, MCP, secret, exfiltration, and inline gateway guardrails.
-
Checks each Claude Code tool call before it runs. Blocks a command that would send one of your keys out, and asks before the agent runs a package or script it copied from…
-
Security guardrails for Claude Code. Intercepts every tool call via PreToolUse hook and evaluates it against your Open Agent Passport (OAP) policy before execution. Blocks…
-
PreToolUse Bash guard for Claude Code that still holds under --dangerously-skip-permissions. Blocks pipe-to-shell installs, disk wipes and fork bombs; asks before rm -rf…
-
Security guard hook for Claude Code. Evaluates every tool call (Bash, Edit, Write, Read, MCP) against 864 pattern-matching rules to block dangerous commands, data exfiltration…
-
DeployShield is a cross-platform production safety guardrail for Claude Code and Gemini CLI. It intercepts terminal commands before execution and blocks dangerous operations…
-
Frictionless security, compliance, and threat detection for Claude Code and Co-Work. Advanced Behavioral detection patterns catch credential exfiltration, reverse shells, prompt…
-
Run Claude Code unattended: capped spend, sandboxed execution, signed receipt, enforced from outside the agent's process.
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
Intent-based security enforcement for Claude Code. ArmorClaude makes Claude declare what it intends to do before doing it, then checks every tool call against that plan. Adds…
-
Security guardrails for Claude Code. Intercepts every tool call via PreToolUse hook and evaluates it against your Open Agent Passport (OAP) policy before execution. Blocks…
-
Security guard hook for Claude Code. Evaluates every tool call (Bash, Edit, Write, Read, MCP) against 864 pattern-matching rules to block dangerous commands, data exfiltration…
-
DeployShield is a cross-platform production safety guardrail for Claude Code and Gemini CLI. It intercepts terminal commands before execution and blocks dangerous operations…
-
Frictionless security, compliance, and threat detection for Claude Code and Co-Work. Advanced Behavioral detection patterns catch credential exfiltration, reverse shells, prompt…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
Operational skill for installing, configuring, operating, and debugging CrowdSec (cscli, LAPI/CAPI, hub, bouncers, WAF/AppSec) across bare-metal, Docker, and Kubernetes.
-
Aikido Security scanning for Claude Code — SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.
-
Semgrep catches security vulnerabilities in real-time and guides Claude to write secure code from the start.
Gelistet auf Claude: knowledge-work-plugins (5)
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
The Vanta plugin connects Claude Code to Vanta's security and compliance platform through the Vanta MCP server. It combines Vanta's test-specific remediation intelligence with…
-
MCP server for terminal commands, file operations, and process management
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
-
Enterprise-grade auth, easy to implement. Add login, SSO, MFA, and access control to any app with framework-aware guidance.
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Codex Security workflows for security scans, analysis, and investigation.
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
Gelistet auf Community GitHub marketplaces (5)
-
macOS security hardening for Claude Code — PreToolUse/PostToolUse hooks that block secret exfiltration, prompt injection, persistence, and self-tampering.
-
Intent-based security enforcement for Claude Code. ArmorClaude makes Claude declare what it intends to do before doing it, then checks every tool call against that plan. Adds…
-
Balanced default runtime security plugin for Claude Code with shell, git, MCP, secret, exfiltration, and inline gateway guardrails.
-
Checks each Claude Code tool call before it runs. Blocks a command that would send one of your keys out, and asks before the agent runs a package or script it copied from…
-
Security guardrails for Claude Code. Intercepts every tool call via PreToolUse hook and evaluates it against your Open Agent Passport (OAP) policy before execution. Blocks…
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Plain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, jargon-free English with…
-
containers
Browse and operate local Docker containers and images in a Copilot canvas. Follow logs, watch resource usage, browse files, inspect image layers, and recover Dockerfile provenance.
-
foundry-hosted-agent-copilotkit
Build CopilotKit + AG-UI web apps on Microsoft Foundry hosted agents (Microsoft Agent Framework): wiring, native Foundry primitives, human-in-the-loop approvals, azd deploy, and…
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Advanced Security plugin for GitHub Copilot.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
Build and manage Microsoft Dataverse solutions using natural language. Includes table/column creation, solution lifecycle, data operations, and MCP server configuration.
Gelistet auf Cursor: cursor/plugins (5)
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Let Grok Bot reach MCP servers on your private Tailscale network. On your own tailnet it joins as one tag:grokbot device; on your team's company tailnet, turned on by a team…
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Scaffold and validate new agent plugins.
-
Build apps, scripts, and automations with the TypeScript SDK.
Gelistet auf Docker MCP Catalog (5)
-
A universal MCP (Model Context Protocol) server to integrate any API with Claude Desktop using only Docker configurations.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
MCP server for terminal commands, file operations, and process management
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
AI interface to troubleshoot and observe Kubernetes/Container workloads.
Gelistet auf Official MCP Registry (5)
-
agent-guardrail io.github.rudimentall1/agent-guardrail
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
-
securecode io.github.juanisidoro/securecode
Secrets vault for Claude Code with audit logs, access rules, and AES-256 encryption.
-
AI security firewall & DLP proxy protecting API keys and blocking destructive commands.
-
Multi-agent LLM security layer detecting prompt injection and jailbreaks.
-
Open-source AI context firewall for governed model, retrieval, memory, and tool access.
Gelistet auf npm registry (MCP servers) (5)
-
guardvibe io.github.goklab/guardvibe
Deterministic security layer your AI can't be. 611 rules, 39 tools, CLI + doctor + host audit.
-
Run SQL queries and inspect database schemas through safe, visible MCP tools.
-
mcp com.dechonet/mcp
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
-
Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.
-
Read-only MCP server exposing the dsh-plugin-certification registry for DeepSeek Harness plugins.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Möchten Sie dieses Zeichen für Ihr Plugin in unserem Katalog?
Belegen Sie mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag, dass Sie es pflegen, und Sie können dieses Zeichen auf der Karte zeigen, dazu Live-Banner für Ihre Website und Ihr README. So funktioniert die Verifizierung
Außerdem erhalten Sie Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Community GitHub marketplaces. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.