cortex-operations

Coordinate Cortex orchestration by analyzing GLOBAL.md and AGENCY.md files.

23|2|Updated Nov 23, 2025
One-click install
npx skills add https://github.com/intertwine/hive-orchestrator --skill cortex-operations
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cortex-operations
Source: https://github.com/intertwine/hive-orchestrator/tree/main/.opencode/skill/cortex-operations
Command: npx skills add https://github.com/intertwine/hive-orchestrator --skill cortex-operations

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Cortex orchestration across multiple projects requires a centralized way to read and reason about project state, dependencies, and readiness, so operators can keep work flowing smoothly.

Core Features & Use Cases

  • Full LLM Analysis: analyzes GLOBAL.md and all AGENCY.md files to identify blockers, propose state updates, and guide actions.
  • Ready Work Detection: quickly identifies unclaimed, actionable work across projects.
  • Dependency Graph Analysis: visualizes blocks, cycles, and relationships to prevent deadlocks.
  • Programmatic Usage: provides commands and usage patterns to discover projects, check readiness, and summarize dependencies.

Quick Start

Run Cortex analysis to read GLOBAL.md and all AGENCY.md files and update project state.

Frequently Asked Questions about cortex-operations

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

FAQPage Schema
How do I coordinate multi-project orchestration and identify blockers across Agent Hive projects?

Multi-project orchestration is coordinated by applying LLM analysis to GLOBAL.md and AGENCY.md files, evaluating dependency graphs and ready-work detection to identify blockers and update project state across multiple projects.

What is ready-work detection and how does it find actionable tasks in project management?

Ready-work detection is a project management feature that analyzes AGENCY.md files to quickly identify unclaimed, actionable work across multiple projects, ensuring operators can keep work flowing smoothly without manual checks.

How do I run Cortex analysis using uv or make commands for project state updates?

Run deterministic Cortex analysis by executing uv or make cortex commands, which triggers LLM evaluation of GLOBAL.md and AGENCY.md files to update project state, detect ready work, and visualize dependency relationships.

Do I need an OPENROUTER_API_KEY to perform LLM analysis on dependency graphs?

Yes, an OPENROUTER_API_KEY is required to perform LLM analysis on dependency graphs, with an optional OPENROUTER_MODEL setting available to specify the model used for analyzing project state and identifying blockers.

Can dependency graph analysis prevent deadlocks in multi-project orchestration workflows?

Dependency graph analysis prevents deadlocks in multi-project orchestration by visualizing blocks, cycles, and relationships across projects, allowing operators to detect potential dependency issues before they halt work flow.

What's the best way to centralize project state tracking across multiple Agent Hive projects?

Centralize project state tracking by using LLM analysis to read GLOBAL.md and all AGENCY.md files, applying dependency-graph evaluation and ready-work detection to maintain an updated view of blockers and actionable work.