AGENTS.md is a project instruction file that gives AI coding agents task context, workflow rules, and constraints so agent behavior aligns with team standards.

Agent Skills are modular capability definitions that package domain-specific guidance, tools, and patterns for recurring agent tasks.

Subagents are narrowly scoped AI assistants that can be invoked by a primary agent to perform specific subtasks more efficiently.

Non-interactive Mode executes agent workflows in a command-driven context without live chat interactions, useful for automation and pipelines.

Automations are recurring or event-based executions that let AI agents perform routine work automatically under predefined instructions.

AI Layer Renaming automatically assigns meaningful layer names based on content and structure. This improves handoff, keeps files consistent with a Design System, and complements reusable Component Properties.

Agent context is the project information, user intent, constraints, and prior conversation an AI agent uses to make accurate changes.

Agent context helps an AI system understand what it is editing and why. Strong context can include the selected page, existing CMS structure, current design patterns, and instructions from the user, which reduces generic or mismatched output.

An agent session is the active connection and conversation state between a user, an AI agent, and the project being edited.

An agent session keeps track of the current project access, recent instructions, and ongoing tasks. Session context helps an agent continue work without starting from a blank slate each time the user asks for a change.

An agent-orchestrated workflow coordinates multiple AI actions, tools, or agents to complete a larger project task.

Agent-orchestrated workflows are useful for multi-step site work such as scanning pages, creating CMS entries, adding links, reviewing changes, and preparing a branch for approval. The orchestration keeps each action aligned with the overall goal.