bulkhead
PreToolUse hooks that keep several Claude Code sessions running on one machine from colliding. Blocks kills by program name (pkill node, taskkill /IM node.exe) and kills that…
Paquete de plugins · de dooly6276
Resumen
bulkhead es un paquete de plugins para herramientas de programación con IA publicado por dooly6276. Marketplaces que leemos y que lo publican: 2 (Community GitHub marketplaces, Copilot CLI: github/awesome-copilot). Lo vimos por primera vez el 2026-11-12 y desde entonces no hemos registrado cambios. Según nuestra pasada por los marketplaces del 2026-11-15.
PreToolUse hooks that keep several Claude Code sessions running on one machine from colliding. Blocks kills by program name (pkill node, taskkill /IM node.exe) and kills that reach another session's processes, dev servers on a port another session uses, heavy commands when RAM is low, git checkout, stash, add -A and commit -a in a tree another session works in, and whole-disk scans such as du -sh ~. Stops servers left by finished sessions. bulkhead scan replays the shell commands in your past transcripts against the guards, read-only, with nothing sent anywhere. Blocks return the reason and an alternative command to the agent; only the user can allow a blocked command, and a repository's own config can only make the guards stricter. It parses command strings and is not a sandbox. Node only, no dependencies.
Qué pide
- Se instala como paquete de plugins
- Hooks declarados: 15
Lo que declara, pide y ejecuta, completo
Instala solo plugins de desarrolladores en los que confíes. Mostramos lo que publican los marketplaces y no probamos plugins.
Funciona con
- Claude Code
- Copilot CLI
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por ti ni probamos plugins.
Como plugin de Claude Code
Generado a partir de lo que declara Community GitHub marketplaces.
/plugin marketplace add davepoon/buildwithclaude
/plugin install bulkhead@buildwithclaudeDónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Copilot CLI: github/awesome-copilot (Abrir el código en GitHub) | Publicado | 0.3.7 | Forks (GitHub): 5 Estrellas (GitHub): 34 |
Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
También figura en un marketplace de la comunidad
| Marketplace | Repositorio | Estrellas (GitHub) |
|---|---|---|
| buildwithclaude | davepoon/buildwithclaude | 3 744 |
Qué contiene el paquete
Tal como se publica en Community GitHub marketplaces.
Skills: 1
bulkhead
Comandos: 6
doctorlogreapremotescanstatus
Hooks: 8
NotificationPostToolUsePostToolUseFailurePreToolUseSessionEndSessionStartStopUserPromptSubmit
Qué cambió
- Apareció en un nuevo marketplace: Copilot CLI: github/awesome-copilot
- Copilot CLI: github/awesome-copilot: apareció
- Pasó a ser un producto que seguimos
- Community GitHub marketplaces: apareció
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta lista.
-
DeployShield is a cross-platform production safety guardrail for Claude Code and Gemini CLI. It intercepts terminal commands before execution and blocks dangerous operations…
-
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…
-
Frictionless security, compliance, and threat detection for Claude Code and Co-Work. Advanced Behavioral detection patterns catch credential exfiltration, reverse shells, prompt…
-
One skill for running Claude Code on Herdr, the terminal agent multiplexer. spawn-session starts a named, detached Claude Code Remote Control session for any project directory in…
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
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…
-
Runtime security for Claude Code: hooks-based observability and blocking, backed by the self-hosted Adrian engine.
-
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…
-
Multi-session awareness for Claude Code. See all active sessions on the same project, get file conflict warnings when two sessions touch the same file, and send messages between…
-
Use Claude Code without fear of data leakage. Unbound enforces command policies, DLP and jailbreak guardrails, and streams session analytics to your security dashboard — all with…
Plugins similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en Claude Code: claude-plugins-community (5)
-
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…
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
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…
-
Multi-session awareness for Claude Code. See all active sessions on the same project, get file conflict warnings when two sessions touch the same file, and send messages between…
Publicado en 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
-
MCP server for terminal commands, file operations, and process management
-
Preset CLI skills for explicit shell, scripting, and CI/CD workflows driven by the `sup` CLI (PyPI package `superset-sup`). Use only for CLI workflows; do not use for MCP-only…
-
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…
-
Aikido Security scanning for Claude Code — SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.
Publicado en Claude: knowledge-work-plugins (5)
-
MCP server for terminal commands, file operations, and process management
-
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…
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
-
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…
-
Build and deploy Base44 full-stack apps with CLI project management and JavaScript/TypeScript SDK development skills
Publicado en 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…
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
Publicado en Community GitHub marketplaces (5)
-
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…
-
One skill for running Claude Code on Herdr, the terminal agent multiplexer. spawn-session starts a named, detached Claude Code Remote Control session for any project directory in…
-
Runtime security for Claude Code: hooks-based observability and blocking, backed by the self-hosted Adrian engine.
-
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…
-
MCP server that orchestrates multiple Claude CLI instances as parallel workers with a real-time dashboard
Publicado en Copilot CLI: github/awesome-copilot (5)
-
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…
-
Model, visualize, and deploy applications with Radius from the GitHub Copilot app and CLI.
-
Helps GitHub Copilot investigate mobile app telemetry, diagnose crashes, manage [bitdrift](bitdrift.ai) workflows and dashboards, integrate the Capture SDK into iOS, Android, and…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
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.
Publicado en 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.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
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…
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
Publicado en Cursor: cursor/plugins (5)
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
Publicado en Docker MCP Catalog (5)
-
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.
-
A Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.
-
Give your AI agents trusted access to the full Postman platform.
Publicado en Official MCP Registry (5)
-
speclock io.github.sgroy10/speclock
AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.
-
Merge gates and safety checks for AI coding agents via MCP.
-
Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
-
Persistent memory and session intelligence for AI coding assistants. Zero config.
-
Secure code execution sandbox for Claude — run Python, JavaScript, and shell commands
Publicado en PyPI (MCP servers) (5)
-
Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.
-
Every tool your AI needs in one self-hosted install: memory, reasoning, git, Docker and more.
-
Undetectable browser automation for AI agents via the Model Context Protocol — one shared backend built for 50+ concurrent Claude Code sessions.
-
A ChatGPT-compatible OAuth MCP server that gives AI coding agents controlled shell, filesystem, remote-worker, and Playwright access inside a local container.
-
marm-mcp-server io.github.Lyellr88/marm-mcp-server
Universal MCP Server with advanced AI memory capabilities and semantic search.
Publicado en npm registry (MCP servers) (5)
-
speclock io.github.sgroy10/speclock
AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.
-
Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
-
MCP server for terminal commands, file operations, and process management
-
Run, watch, and meter coding agents — Claude Code, OpenCode, Kiro, Codex CLI, Gemini CLI, Prime Agent — with normalized events, cost accounting, A/B experiment/variant comparison…
-
Install, configure, diagnose, and upgrade Satori's local-first MCP runtime for Claude Code, Codex, and OpenCode.
Encontrados por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Quieres esta marca para tu plugin en nuestro catálogo?
Demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS, y podrás mostrar esta marca en la ficha, con banners en vivo para tu web y tu README. Cómo funciona la verificación
Además recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Añada un banner dinámico a su README o sitio web
Muestre datos actualizados del catálogo en su sitio web o README de GitHub. Elija un banner dinámico o una insignia compacta.
Datos de Community GitHub marketplaces. Datos de Copilot CLI: github/awesome-copilot. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.