richfrem

A system architecture scaffolder designed to synthesize visual discoveries and interactive Q&A responses into comprehensive C4 and TOGAF specs.

Triggers the L5 Red Team Sub-Agent to rigorously audit a plugin against the 39-point L4 pattern matrix.

Scaffold a complete Claude Code plugin from scratch

(Industry standard: Meta-Learning System / Automated Autoresearch) Primary Use Case: Continuous, self-improving orchestration of an agentic system over multiple sessions. Use when: building a continuous improvement layer that autonomously identifies workflow friction, postulates hypotheses, and tests improved instructions/coding skills against an objective headless benchmark before merging and per

Systematically analyze agent plugins and skills to extract design patterns, architectural decisions, and reusable techniques. Trigger with "analyze this plugin", "mine patterns from", "review plugin structure", "extract learnings from", "what patterns does this plugin use", "check if this plugin is well-structured", "validate plugin compliance", or when examining any plugin or skill collection to

ADR management skill. Auto-invoked for generating architecture decisions, documenting design rationale, and maintaining the decision record log. Uses native read/write tools to scaffold and update ADR markdown files.

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 up an improvement lab, filling a capability gap, or coordinating multiple loops.

Reviews a completed os-eval-runner lab run and backports approved changes to master plugin sources. Trigger with "backport the eval results", "review the lab run", "apply eval improvements to master", "check what the eval agent changed".

Codifies the plan-and-delegate workflow for evolving plugins, skills, and agents. Given a target (plugin/skill/agent name) and an evolution goal, this skill first brainstorms 2-3 approach options using the cheapest available model, presents them for selection, then writes a structured task plan and Copilot CLI delegation prompt for the chosen approach. Called by os-architect for Path B (update) an

Maintains a persistent, folder-based log of all agentic-os experiment runs. Each run writes one dated file to context/experiment-log/ and updates index.md. Supports five source types: verifier (qualitative), tester (qualitative), orchestrator (numeric), planner (qualitative), survey (mixed). Handles both numeric results (eval scores, KEEP/DISCARD, delta) and qualitative results (PASS/FAIL/PARTIAL,

Bootstraps a skill evaluation lab repo for an autoresearch improvement run. Trigger with "set up an eval lab", "bootstrap the eval repo", "prepare the test repo for skill evaluation", "create an eval environment for this skill", "set up the lab space for this skill", or when starting a new skill optimization run that needs a standalone test environment.

Stateless evaluation engine that scores and gates skill improvement iterations using headless Python evaluation scripts. Use when the user says "evaluate this skill", "run autoresearch loop on", "optimize this skill", "run the eval loop", or when another agent proposes a change to an existing skill and needs empirical validation before applying it. Supports autonomous loop mode for iterative impro

Activate when the user wants to create a new APM-native package from scratch for reusable agent skills, agents, commands, hooks, MCP configuration, prompts, or governance-managed agent assets. Do not use this for existing plugin migration; use convert-plugin-to-apm instead.

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 says "optimize my CLAUDE.md", "audit agent instructions", "improve my CLAUDE.md",

Safely removes all agent lock files from the context/.locks/ directory to resolve deadlocks caused by crashed agents leaving stale locks behind. Use when the user says "/os-clean-locks", "clear all locks", "reset agent locks", or when an agent is deadlocked and cannot acquire a lock because a previous agent crashed and left a stale lock behind in context/.locks/. Verifies lock existence, discovers

Discovers and persists the user's available AI environments (Claude, Copilot CLI, Gemini CLI, Cursor, etc.) to context/memory/environment.md. Run once after OS setup or whenever the environment changes. os-architect and os-evolution-planner read this file to select the right delegation backend and cheapest brainstorm model automatically. Invoked by os-architect on first run if environment.md is ab

Verifies that os-architect actually causes evolution — not just words. Dispatches os-architect in single-shot simulation mode for a given test scenario, then checks for real artifact presence (new files, HANDOFF_BLOCK, plan files). Reports PASS / FAIL with grep evidence. Accumulates results into a test report. Use after any changes to os-architect, os-evolution-planner, or improvement-intake-agent

Trigger with "explain agentic os", "how do I set up a persistent agent environment", "what is the CLAUDE.md hierarchy", "explain the context folder structure", "how does session memory work", "what is soul.md or user.md", "explain auto-memory or MEMORY.md", "what is a loop scheduler or heartbeat", or when the user asks for the canonical guide.

Pattern 5: Concurrent Event-Driven Multi-Agent Loop. Coordinates multiple Claude sessions as OS threads sharing a common event bus and memory address space. Every loop cycle is a full improvement cycle: execute, eval against benchmark (KEEP/DISCARD), emit friction events during work, close with post_run_metrics, agent self-assessment survey saved to retrospectives, memory persistence, and Triple-L

Trigger with "show me the improvement chart", "how are we improving", "progress report", "graph the eval scores", "show cycle of improvement", "what's the trend", "are we getting better". Produces a visual/text summary of how the agentic loop is improving across cycles. Do NOT use this to run the learning loop or evaluate a specific skill change.

Trigger: "set up agentic OS", "initialize agent harness", "init my project for AI agents", "where do I put CLAUDE.md", "create my agent environment", "set up persistent memory". Guides users through an interview to understand their use case, then scaffolds the right Agentic OS structure. Use even when the user just asks WHERE to put files.

Trigger with "remember this", "update memory", "what should we record from this session", "capture learnings", "write a session log", or when closing a session. Guides agents on managing memory hygiene across sessions, deciding what to write to dated memory logs, what to promote to long-term memory.md, and when to archive. <example> User: I'm done for the day, can you write up a session log? Agent

Self-healing and self-evolving pattern for agents operating against external systems (CDP automation, DOM-dependent tooling, web APIs). Classifies failures into three tiers — Gap / Failure / Regression — applies repo-profile-gated edits with appropriate autonomy, verifies the fix, and updates domain reference files ("The Map, not the Diary"). Invoke whenever a tool call or subprocess returns a fai

Audit a file for TODO comments, pending work items, or technical debt markers. Useful for checking code readiness before a commit or reviewing task status. Trigger with "check for todos", "audit for debt", "list pending work", or "scan for TODOs".

(Industry standard: Parallel Agent) Primary Use Case: Work that can be partitioned into independent sub-tasks running concurrently across multiple agents. Parallel multi-agent execution pattern. Use when: work can be partitioned into independent tasks that N agents can execute simultaneously across worktrees. Includes routing (sequential vs parallel), merge verification, and correction loops.

(Industry standard: Sequential Agent / Agent as a Tool) Primary Use Case: Delegating a well-defined task to a worker agent, verifying its execution, and repeating if necessary. Inner/outer agent delegation pattern. Use when: work needs to be delegated from a strategic controller (Outer Loop) to a tactical executor (Inner Loop) via strategy packets, with verification and correction loops.

(Industry standard: Loop Agent / Single Agent) Primary Use Case: Self-contained research, content generation, and exploration where no inner delegation is required. Self-directed research and knowledge capture loop. Use when: starting a session (Orientation), performing research (Synthesis), or closing a session (Seal, Persist, Retrospective). Ensures knowledge survives across isolated agent sessi

(Industry standard: Routing Agent / Orchestrator Pattern) Primary Use Case: Analyzing an ambiguous trigger and routing it to one of the specific specialized implementations. Routes triggers to the appropriate agent-loop pattern. Use when: assessing a task, research need, or work assignment and deciding whether to run a simple learning loop, red team review, dual-loop delegation, or parallel swarm.

(Industry standard: Review and Critique Pattern) Primary Use Case: Iterative generation paired with adversarial review, continuing until an 'Approved' verdict is reached. Orchestrated adversarial review loop. Use when: research, designs, architectures, or decisions need to be reviewed by red team agents (human, browser, or CLI). Iterates in rounds of research → bundle → review → feedback until app

This skill should be used when the user asks to "audit a plugin", "validate my plugin", "check plugin structure", "verify plugin is correct", "validate .claude-plugin/plugin.json", "check if my plugin is compliant", "review plugin components", or mentions plugin validation or structure compliance. Also trigger proactively after the user creates or modifies any plugin component (commands, agents, s

Activate when the user wants to compile an APM package into top-level context documents such as AGENTS.md, CLAUDE.md, or GEMINI.md, especially for Codex, Gemini, OpenCode, or agents-protocol style hosts. Do not use when the user only needs per-skill installation; use install-apm-package instead.

Activate when the user wants to add APM governance, lockfile/audit readiness, or multi-runtime package management to an existing Claude/Copilot/agent plugin, or explicitly convert a plugin into an APM-native package.

Scaffold a GitHub agentic workflow from an existing skill

Deploy a skill as an Azure AI Foundry hosted agent

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define a command with arguments", "create a command that runs bash", "add a /command to my plugin", "use $ARGUMENTS in a command", "set up argument-hint", "create a workflow command", "interactive command", or needs guidance on slash command structure, YAML frontmatter fields, file

Scaffold an agent skill with Docker runtime support

Scaffold a deterministic GitHub Actions CI/CD workflow

Design and scaffold an event-driven Claude Code hook

Add an MCP server integration to a plugin

Scaffolds the filesystem structure for a new agent skill: creates the directory layout, writes a starter SKILL.md, generates evals/evals.json, references/, scripts/, and assets/ as needed, and runs a discovery interview to capture name, purpose, and trigger phrases before writing any files. Use when the user says "create a new skill", "scaffold a skill", "generate a skill", "new skill setup", or "

Scaffold an advanced stateful agent skill with L4 patterns

Design and scaffold a Claude Code sub-agent

Provides information about how to create, structure, install, and audit Agent Skills, Plugins, Antigravity Workflows, and Sub-agents. Trigger this when specifications, rules, or best practices for the ecosystem are required.

Provides active execution protocols to rigorously audit how code, directory structures, and agent actions comply with the authoritative ecosystem specs. Trigger when validating new skills, plugins, or workflows.

Trigger with "evaluate autoresearch fit", "score this skill for karpathy loop", "is this a good autoresearch candidate", "assess autoresearch viability for", "which skills are best for autonomous loop optimization", "score skills for 3-file architecture", or when the user wants to determine if a skill is a good candidate for applying the Karpathy autoresearch autonomous optimization loop pattern.

Fixes broken path references in plugin skill and agent files to ensure portability across installed environments. Use when you see "plugins/" paths in SKILL.md or agent files, need to standardize path references after installing a skill, want to audit and fix cross-plugin path dependencies, run a portability audit on a repository, neutralize hardcoded machine paths like /Users/, find Python script

Activate when the user wants to install, deploy, test, or materialize an APM package into runtime directories such as .agents/, .github/, .claude/, .cursor/, .gemini/, .codex/, .opencode/, or .windsurf/. Use after creating or converting an APM package.

Performs an uncompromising L5 Enterprise Red Team Audit on a given plugin against the 39-point architectural maturity matrix. Trigger when the user requests a security audit, red team assessment, structural compliance review, or maturity gap analysis of any agent plugin or skill directory.