Agentic OS Control Plane: deterministic state-machine governance for AI coding agents with cryptographically enforced SSH/CIBA human-in-the-loop gates and zero-trust verification.
This repository also configures its own agents. See what agent-plugins-skills tells them →
Plugin Claude Code
Bundles 14 skills, 2 agents, 3 hooks · 2,622 tokens together
An opinionated learning layer and harnessing discipline above what Claude Code ships natively. Provides a structured memory hierarchy, a continuous improvement loop for model instructions, multi-agent event bus coordination, and an eval-gated skill improvement system. Designed for developers running long-horizon…
Plugin Claude Code
Bundles 13 skills, 9 agents · 1,811 tokens together
Unified Cognitive Memory & Retrieval Suite. Integrates RLM distills (summarization), ChromaDB vector semantic search, and session caching / tiered promotion-demotion memory management.
Plugin Claude Code
Bundles 10 skills, 1 agent · 548 tokens together
Composable agent loop and graph architectures for learning loops, deterministic state machines, agent orchestration (0-to-N inner agents), parallel swarms, and red team coordination. Framework-agnostic: works with any CLI agent (Claude, Gemini, Copilot, OpenHands, etc.).
Plugin Claude Code
Bundles 24 skills · 1,258 tokens together
Meta-plugin containing ecosystem generation and evolution auditing primitives. Includes scaffolding for Agent Skills, Plugins, CLI sub-agents, custom GitHub Copilot agents, GitHub Agentic Workflows (gh-aw), CI/CD Smart Failure agents, Azure Foundry agents, and comprehensive evolution auditing (audit-plugin…
Plugin Claude Code
Bundles 11 skills, 13 agents · 1,209 tokens together
Multi-LLM Task Router Suite. runagent.py routes bounded tasks to six backends: Claude CLI, GitHub Copilot, Gemini CLI, Antigravity (Agy), Codex/OpenAI-compatible, and direct local Gemma 4 12B via llama-server (2s, no proxy). 13 expert agent personas covering adversarial patterns (red-team, critical audit, debate synt.
Plugin Claude Code
Bundles 1 skill · 65 tokens together
Python dependency management with pip-compile locked-file workflow and tiered hierarchy for Python backends.
Plugin Claude Code
Bundles 19 skills · 1,186 tokens together
Unified Developer Utilities Suite — 19 skills consolidated from standalone plugins. Covers ADR management, coding conventions, context bundling, Mermaid diagram rendering, GitHub issue logging & friction management, GitHub issue backlog bridge, issue prioritizer & Projects v2 sync, GitHub issue worktree manager…
Plugin Claude Code
Bundles 20 skills, 15 agents · 2,135 tokens together
Autonomous discovery, business requirements capture, and prototyping loop for spec-driven engineering. Programmatic phase-gate enforcement via exploration-workflow.
Plugin Claude Code
Bundles 10 skills, 1 command, 2 agents · 884 tokens together
Obsidian Wiki Engine - Karpathy-style LLM wiki + RLM distillation + vector search. Dual-representation knowledge graph: vault operations, cross-source concept synthesis, wiki node generation, RLM distillation, semantic health linting, graph traversal, canvas, bases, and progressive-disclosure query with vector DB…
Plugin Gemini CLI
Universal Agent Plugins & Skills repository extension for Gemini CLI.
Plugin Claude Code
Bundles 3 skills · 207 tokens together
Orchestration hub for the plugin ecosystem. Manages structural audits, agent environment sync, cross-repo plugin replication, and Universal Bridge Installation to adapt standard plugins to 30+ target environments (GitHub Copilot, Gemini, Cursor, Roo, etc).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: