By georgeharker
Manage shared backend processes through the `sharedserver` CLI. SessionStart attaches via `sharedserver use`; SessionEnd detaches via `sharedserver unuse`. Multiple Claude Code sessions share a single backend; the server survives session restarts within its grace period.
Executables (bin/) — files in this plugin's bin/directory are added to the Bash tool's PATH while the plugin is enabled.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimManage the mcp-combiner process across Claude Code sessions via the sharedserver CLI, and auto-register its HTTP endpoint as the 'mcp-combiner' MCP server. SessionStart attaches; SessionEnd detaches. Combiner survives Claude restarts within the grace period and is shared with other clients (nvim, OpenCode) that use the same name.
Manage shared backend processes through the `sharedserver` CLI. SessionStart attaches via `sharedserver use`; SessionEnd detaches via `sharedserver unuse`. Multiple Claude Code sessions share a single backend; the server survives session restarts within its grace period.
Structured, hierarchical SVG authoring for an LLM with a render-and-see feedback loop, backed by an inkex document model.
Structured, hierarchical SVG authoring for an LLM with a render-and-see feedback loop, backed by an inkex document model.
Register `ruff server` as the Python LSP. Surfaces ruff diagnostics and code actions via LSP. Mutually exclusive with the `pylsp` plugin — only one server can claim `python`.
npx claudepluginhub georgeharker/claude-sharedserver --plugin claude-sharedserverUltra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
Memory compression system for Claude Code - persist context across sessions
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
45% cost reduction measured. Cache expiry prevention, SubTask auto-delegation, zero-cost context restoration, real-time cost dashboard. The only Claude Code plugin built from CC source analysis.