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…
Plugin bundle · by dooly6276
About
bulkhead is a plugin bundle for AI coding tools published by dooly6276. Marketplaces we read that list it: 2 (Community GitHub marketplaces, Copilot CLI: github/awesome-copilot). We first saw it on 2026-11-12 and have recorded no change since. As of our marketplace pass on 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.
What it asks for
- Installs as a plugin bundle
- Hooks: 15
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Works with
- Claude Code
- Copilot CLI
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a Claude Code plugin
Built from what Community GitHub marketplaces declares.
/plugin marketplace add davepoon/buildwithclaude
/plugin install bulkhead@buildwithclaudeWhere it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Copilot CLI: github/awesome-copilot (Open the source on GitHub) | Listed | 0.3.7 | Forks (GitHub): 5 Stars (GitHub): 34 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
Also listed in one community marketplace
| Marketplace | Repository | Stars (GitHub) |
|---|---|---|
| buildwithclaude | davepoon/buildwithclaude | 3 744 |
What the bundle contains
As published on Community GitHub marketplaces.
Skills: 1
bulkhead
Commands: 6
doctorlogreapremotescanstatus
Hooks: 8
NotificationPostToolUsePostToolUseFailurePreToolUseSessionEndSessionStartStopUserPromptSubmit
What changed
- Appeared on a new marketplace: Copilot CLI: github/awesome-copilot
- Copilot CLI: github/awesome-copilot: appeared
- Became a product we track
- Community GitHub marketplaces: appeared
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
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…
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on 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…
Has a listing on 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.
Has a listing on 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
Has a listing on 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.
Has a listing on 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
Has a listing on 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.
Has a listing on 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.
Has a listing on 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.
Has a listing on 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.
Has a listing on 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
Has a listing on 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.
Has a listing on 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.
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Want this mark on your plugin in our catalog?
Prove you maintain it with a file in its repository, a file on your domain or a DNS record, and you can show this mark on the card, with live banners for your site and README. How verification works
You also get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Add a live banner to your README or site
Show up-to-date catalog facts on your website or GitHub README. Choose a live banner or a compact badge.
Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the public marketplace file https://github.com/github/awesome-copilot/blob/HEAD/.github/plugin/marketplace.json. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.