Teams often use the same word for instructions, capabilities, tools, workers, and controls. These source-backed comparisons make the decision boundary explicit—and show when two layers work better together.
8
decision guides
Primary docs
evidence standard
30 days
maximum review interval
Decision 01
Use AGENTS.md for concise repository truth that should shape most sessions. Use a Skill for a specialized procedure that should load only when the task calls for it.
Where should durable agent instructions and repeatable workflows live?
Open comparisonDecision 02
A Skill is a focused unit of reusable knowledge or procedure. A plugin is a distribution boundary that can package Skills with agents, hooks, tools, and connectors.
Should a capability be one portable workflow or an installable extension bundle?
Open comparisonDecision 03
Subagents divide bounded work inside an active agent session. Automations run a stable workflow later or repeatedly, with durable scheduling, permissions, and recovery.
Should work be delegated inside a live session or run unattended on a trigger?
Open comparisonDecision 04
MCP exposes tools, resources, and prompts to a client. A2A exposes an independently operated agent that accepts messages, manages task state, and returns artifacts.
Does an agent need a tool, or does it need to collaborate with another agent?
Open comparisonDecision 05
AGENTS.md carries deliberate team-owned repository instructions. Memory stores inspectable observations or preferences that may evolve across sessions.
Should information be remembered dynamically or committed as shared project guidance?
Open comparisonDecision 06
Instructions guide model judgment. Hooks run deterministic handlers at defined lifecycle events regardless of whether the model remembers to invoke them.
Should the model be told to do something, or should the system enforce it?
Open comparisonDecision 07
A Skill teaches the agent how to perform a workflow. MCP connects the agent to tools, resources, or prompts supplied by a server.
Does the agent need new knowledge and procedure, or access to an external capability?
Open comparisonDecision 08
Prompt guardrails communicate intent and decision policy. Permissions, sandboxes, approval gates, and scoped credentials enforce what actions are actually possible.
Which safety boundaries belong in instructions, and which require platform enforcement?
Open comparison