18 tagged agent-infrastructure, measured the same way as everything else here.
Plugin Claude Code
Bundles 30 skills, 11 commands, 5 agents, 6 hooks, 1 MCP server · 2,209 tokens together
Install, deploy, and operate agent-swarm: Docker Compose, Kubernetes with Helm, HTTPS, agent-fs, integrations, and the API for coding agents.
Plugin Claude Code
Bundles 1 skill, 9 hooks · 50 tokens together
Persistent semantic memory for Claude Code — user preferences, project context, prior decisions, and codebase facts that survive across sessions.
haoruilee/awesome-agent-native-services
Plugin Claude Code
Bundles 4 skills · 246 tokens together
Skills for discovering, installing/connecting, evaluating, and contributing to the Awesome Agent-Native Services catalog.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 130 tokens together
Give Claude shared, permission-aware company context, durable organizational memory, and governed actions through Lobu MCP.
Plugin Claude Code
Bundles 19 skills, 1 hook · 3,813 tokens together
A Buddhist teaching plugin with 14 prebuilt teacher personas from Chinese, Tibetan, and Theravada traditions, plus tools for comparing teachers, holding debates, and building courses.
Plugin Claude Code
Plugin marketplace listing 1 plugin: inkbox.
Plugin Claude Code
Cheaper, sharper Claude Code sessions: Bash output trimmed before Claude reads it, a project map and this project's field notes at session start, iq code search and fileq document reading taught, and /intentic:stats to show what each one saved. Every mechanism is a switch in /config.
eriknewton/sanctuary-framework
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 194 tokens together
Open source wall under your AI agent: egress enforced by the OS on macOS, keys the operator holds, a hash-chained audit record. Linux: proven on Ubuntu 24.04 (x86-64) only. Wraps Claude Code, Cursor, Hermes, OpenClaw and Cline on tested config paths (Assurance Matrix: partial).
Plugin Claude Code
Bundles 1 command, 1 hook · 17 tokens together
Run Claude Code unattended: cap the spend, sandbox execution, and get a signed receipt, enforced from outside the agent's own process by the covguard binary.
Plugin Gemini CLI
Maidan MCP server - agent coordination for your own instance.
Plugin Claude Code
Bundles 14 skills, 1 command, 4 agents, 11 hooks · 1,537 tokens together
Portable AI agent harness — curated review/build/test agents, secret-hardening + worktree + plan-gate hooks, and spec/supervise/wrap/verify-completion skills. Install once, use in every project. AI-agnostic core (Claude Code / Codex / Antigravity).
Plugin Claude Code
Bundles 4 skills, 7 commands · 727 tokens together
Decentralised scriptwriter recognition + co-brainstorm — REAL RECOGNISE REAL cascades, signed writers' rooms, chaos cards, and a 15-tool MCP surface. Drop into /.claude/ to give Claude Code six slash commands and three skills.
Plugin Gemini CLI
Find repeated expensive read-only checks, duplicate tool calls, and cold concurrent misses in AI agent workloads before native-first, policy-gated reuse.