Skip to content

Entry

Bulkhead

Appears in 5 awesome lists

Guards for machines that run many Codex and other agent sessions at once: a PreToolUse hook on Bash blocks name-based process kills, port collisions, destructive git commands on another session's worktree, whole-disk scans and long foreground sleeps, and holds heavy commands back when RAM runs low.

Open github.comdooly6276/claude-bulkhead

Found in these lists

Awesome Agent Orchestrators

Section: Agent Infrastructure & Primitives · PreToolUse hooks for Claude Code that stop parallel sessions and their subagents on one machine from killing each other's processes, clashing on ports, committing each other's edits, or running heavy commands when RAM is low.

FreshScore 86

Awesome Ai Plugins

Section: Development & Workflow · Pre-tool-use hooks for Claude Code, Codex, Gemini CLI, Cursor and OpenCode that stop one agent session from killing another session's processes, taking its port, or stashing, resetting or checking out over its uncommitted work on the same machine.

FreshScore 86

Awesome Codex Plugins

Section: Development & Workflow · Guards for machines that run many Codex and other agent sessions at once: a PreToolUse hook on Bash blocks name-based process kills, port collisions, destructive git commands on another session's worktree, whole-disk scans and long foreground sleeps, and holds heavy commands back when RAM runs low.

FreshScore 88

Awesome Gemini CLI

Section: Commands & Extensions · Gemini CLI extension for machines that run many agent sessions at once (several Gemini CLI, Claude Code or Codex sessions in separate worktrees of one app). A BeforeTool hook on run_shell_command blocks name-based kills of another session's processes, port collisions, git commands that would…

FreshScore 88

Awesome Harness Engineering

Section: Security, Sandbox & Permissions · PreToolUse hooks that keep parallel Claude Code sessions on one machine from interfering with each other: they block name-based process kills, port clashes, heavy commands when RAM is low, git add -A in a tree another live session is editing, and whole-disk scans, and return the reason and a safer…

FreshScore 93

OrcaReplay

by Continuum AI - Records a Claude Code run through a local proxy and replays it offline, reproducing it byte-for-byte with the network off, or forking it from any checkpoint onto a different model. Capture happens below the harness, so shell exit codes, per-turn file changes and MCP calls land on…

In 14 listsDetails

deja-vu

Indexes coding-agent sessions already written to disk and serves them back over MCP with no LLM calls, embeddings, or API keys. The zero-dependency binary solves the memory cold-start problem for cross-session persistence and demonstrates that agent memory can be built on existing filesystem…

In 11 listsDetails

Supercov

Coverage, security and code quality for coding agents. Gemini CLI extension that runs the project's existing tests, measures line, branch and MC/DC coverage, and hands Gemini the untested code to test next. Install with gemini extensions install https://github.com/supercorp-ai/supercov.

In 9 listsDetails

YYLO

Command-line orchestrator for coding agents, repeatable workflows, and receipt-backed repository changes. Each task freezes the protected target SHA and creates a dedicated branch/worktree behind typed task, validation, merge, and release-readiness boundaries; the merge queue owns risk-based…

In 10 listsDetails

Archcore

스펙, 아키텍처, 결정(ADR), 규칙, 계획을 저장소의 .archcore/에 Git으로 관리하고 CLI·MCP 서버·플러그인으로 AI 코딩 에이전트에 프로젝트 컨텍스트를 제공. CLI는 끌 수 없는 자동 업데이트를 하며(쓰기 권한이 없는 경로에 설치하면 멈춤), 설치·업데이트 통계를 전송(DO_NOT_TRACK=1로 해제)

In 8 listsDetails

Orbi

Picks up GitHub Issues labeled ai-ready, implements each in an isolated worktree, has a separate session review the PR against the Issue's acceptance criteria, then merges only the reviewed head and cuts a tagged release. Runs on Pi with any OpenAI-compatible API or a Codex subscription.

In 7 listsDetails

StyleSeed

by kiwiman - A design engine that takes a different tack from "feed the model more tokens": it teaches design judgment — ~74 rules pros carry but never write down ("the refined black isn't #000, it's #2A2A2A"; "one accent color, everything else grayscale") — as plain markdown the agent reads…

In 5 listsDetails

Research Agent Skills

280+ Agent Skills that turn Claude Code, Codex, Cursor, Gemini CLI and other agents into a research co-scientist for literature reviews, hypotheses, experimental design, data analysis in biology, chemistry, medicine, physics and ML, paper writing, citation verification against Crossref, OpenAlex…

In 5 listsDetails