agent-infrastructure-scorecard

Monitors InProc vs LangGraph Server discrepancies in Cogni agent infrastructure across graphs, executors, and evals.

4|5|Updated Nov 5, 2025
One-click install
npx skills add https://github.com/cogni-dao/cogni --skill agent-infrastructure-scorecard
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-infrastructure-scorecard
Source: https://github.com/cogni-dao/cogni/tree/main/.claude/skills/agent-infrastructure-scorecard
Command: npx skills add https://github.com/cogni-dao/cogni --skill agent-infrastructure-scorecard

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Living state tracking for Cogni agent infrastructure, enabling comparison between InProc and LangGraph-Server implementations, alignment checks, and inventory drift detection across graphs, executors, and evals. The stable mental model lives in agent-infrastructure-expert; this scorecard captures the dated state that moves as graphs, executors, and evals ship. Use to check "what's actually built vs paper", "where do InProc and Server diverge", "which agent specs are stale/duplicated/safe-to-delete". Update THIS, not the expert skill.

Core Features & Use Cases

  • Alignment monitoring between InProc and LangGraph Server I/O and behavior to surface divergences.
  • Drift and consolidation tracking to inform updates to the expert model and maintain a single source of truth.
  • State verification and provenance for agent infrastructure components, relationships, and evolving rules.

Quick Start

Run the latest scorecard check to surface discrepancies and refresh the living view with the newest graphs, executors, and evals.

Frequently Asked Questions about agent-infrastructure-scorecard

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I monitor drift between InProc and LangGraph Server implementations?

Inventory drift detection tracks evolving graphs, executors, and evals to identify stale or duplicated agent specs. By capturing dated state movements, it informs updates to the expert model and flags components that are safe to delete.

What is infrastructure alignment checking for agent graphs and executors?

Versioned state comparison evaluates dated infrastructure states by contrasting InProc and LangGraph Server components. It provides provenance for agent infrastructure relationships and evolving rules, ensuring a single source of truth during consolidation.

How do I track live state for Cogni agent infrastructure graphs and executors?

State verification validates agent infrastructure components, relationships, and evolving rules by capturing dated state movements. It provides provenance for infrastructure tracking, ensuring accurate comparisons between actual builds and documented specifications.

How do I identify stale or duplicated agent specs in my infrastructure?

Alignment monitoring surfaces divergences between InProc and LangGraph Server I/O and behavior. By tracking these discrepancies, it maintains a single source of truth and informs necessary updates to the stable expert mental model.