Plugin Claude Code
A curated collection of AI agent plugins and skills for Claude Code — covering spec-driven development, memory management, context bundling, multi-agent orchestration, CLI sub-agents, and more.
Agent
Trigger with "use the agentic-os-setup agent", "run the setup agent", "set up an agentic OS", "persist memory", "add the OS harness", or when the user requires memory persistence, repository-level conventions, or autonomous background loops. Directs the orchestration, synthesis, and provisioning of a persistent AI…
Agent
Repository hygiene agent that maintains the Plugin Ecosystem index in README.md.
Agent
Front-door intake agent for the Agentic OS improvement lifecycle. Runs before any skill evaluation begins. Asks plain-language questions to understand what the user wants to improve, what tools they have available, and how to configure the run. Produces a run-config.json and a session-brief.md that downstream agents…
Agent
Front-door intake agent for Agentic OS ecosystem evolution. Classifies user intent (pattern abstraction, research application, lab setup, capability gap fill, or multi-loop orchestration), audits existing capabilities, proposes the right evolution path (orchestrate existing / update existing / create new), and…
Agent
Validation agent for os-architect. Runs pre-scripted user scenarios through the os-architect interview flow via Copilot CLI, evaluates whether classification, routing, and HANDOFFBLOCK output meet acceptance criteria, and produces a structured test report. Use to battle-harden os-architect after changes, or to…
Agent
Trigger with "run health check", "check os metrics", "system monitor", or when the user wants to review the Agentic OS liveness metrics across the Event Bus, locks, and memory arrays. user: "Run a system monitor check on the OS." assistant: "I'll execute the os-health-check agent to scan the event bus and state file."…
Instructions file GitHub Copilot
Instructions for richfrem/agent-plugins-skills, covering copilot instructions for agent-plugins-skills, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
Instructions file CodexOpenCode
Instructions for richfrem/agent-plugins-skills, covering agents.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
Instructions file
Instructions for richfrem/agent-plugins-skills, covering claude.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
Instructions file Gemini CLI
Instructions for richfrem/agent-plugins-skills, covering gemini.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
Plugin Claude Code
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…
Agent
Audits closed GitHub issues to verify whether root causes were genuinely resolved, if follow-on execution friction appeared, or if systemic improvements were retained.
Agent
Consumes frictionclusteragent hotspot reports to auto-propose and synthesize systemic refactoring PRs for Tier 3 architecture friction.
Command
Front-door intake for Agentic OS evolution — classifies intent, audits existing capabilities, proposes a path (A/B/C), and dispatches implementation work via Copilot CLI.
Command
Bootstrap the project by triggering the agentic-os-setup conversational architect.
Command
Run a full OS improvement cycle — execute, eval, emit friction events, close with post-run metrics, and trigger a Triple-Loop Retrospective if the friction threshold is crossed.
Command
Force garbage collection and conflict resolution on the tiered memory system.
Hook
Runs when a session starts, executing session_start.py via python3. From richfrem/agent-plugins-skills.
Hook
Runs after a tool call finishes, executing update_memory.py via python3. From richfrem/agent-plugins-skills.
Hook
Runs when the agent finishes a response, executing post_run_metrics.py via python3. From richfrem/agent-plugins-skills.
Skill Claude CodeCodex
Conducts a full-system adversarial audit of agent plugins, skills, and orchestration against enforced runtime contracts using deep reasoning (GPT5.5-equivalent thinking).
Skill Claude CodeCodex
Audits and rewrites AI agent instruction files (CLAUDE.md, GEMINI.md, .github/copilot-instructions.md) in any repo. Strips stale or foreign content, applies Karpathy's four behavioral principles, ensures platform-specific sections, and makes each file authoritative rather than a copy of another. Trigger when the user…
Skill Claude CodeCodex
SME-facing front-door skill for Agentic OS ecosystem evolution. Invokes the os-architect interview flow: classifies intent, audits existing capabilities, proposes evolution path (orchestrate / update / create), and dispatches work. Use when evolving plugins, skills, or agents — whether applying a new pattern, setting…