codified-context-architecture

Organizes AI agent knowledge into hot memory, specialists, and cold-memory subsystems.

13|3|Updated Mar 2, 2026
One-click install
npx skills add https://github.com/phrazzld/agent-skills --skill codified-context-architecture
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: codified-context-architecture
Source: https://github.com/phrazzld/agent-skills/tree/main/core/codified-context-architecture
Command: npx skills add https://github.com/phrazzld/agent-skills --skill codified-context-architecture

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the challenge of managing and organizing knowledge for AI agents, preventing information overload and ensuring efficient retrieval by structuring it into distinct memory tiers.

Core Features & Use Cases

  • Tiered Knowledge Management: Organizes information into Hot Memory (always loaded), Specialists (domain-specific agents), and Cold Memory (on-demand docs).
  • Placement & Routing Rules: Provides clear guidelines on where to store different types of knowledge and how to route requests to the appropriate specialist or document.
  • Drift Detection: Helps maintain the accuracy of documentation by identifying when source files change and documentation needs review.
  • Use Case: When designing the knowledge base for a new AI agent, use this skill to establish a scalable and maintainable structure for its operational data.

Quick Start

Use the codified-context-architecture skill to organize project knowledge for AI agents.

Frequently Asked Questions about codified-context-architecture

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

FAQPage Schema
What is tiered context architecture for AI agents?

Tiered context architecture organizes project knowledge for AI agents into hot memory, specialist routing, and cold-memory subsystem docs. This structure prevents information overload and ensures efficient retrieval by defining strict placement, routing, and drift rules for operational data.

How do I structure knowledge for a new AI agent?

To structure knowledge for an AI agent, organize information into hot memory for always-loaded context, specialists for domain-specific routing, and cold memory for on-demand subsystem docs. This establishes a scalable, maintainable base for operational data.

When should I replace a single-file manifest with tiered context?

Replace a single-file manifest with tiered context when you need scalable knowledge management and efficient AI retrieval. This approach prevents information overload by splitting operational data into hot memory, specialist routing, and cold-memory docs.

How do I manage documentation drift in AI agent infrastructure?

Manage documentation drift by applying rules that identify when source files change and documentation needs review. This maintains accuracy across hot memory, specialist routing, and cold-memory subsystem docs within the agent infrastructure.

Does tiered context architecture work for domain-specific AI routing?

Yes, tiered context architecture works for domain-specific AI routing by defining specialist tiers. It provides clear guidelines on where to store domain knowledge and how to route requests to the appropriate specialist or document efficiently.