[FEATURE]: Agent-scoped skill loading — only load skills declared by the active agent #19344

• I have verified this feature I'm about to request hasn't been suggested before.

Describe the enhancement you want to request

When an agent is active, all discovered skills are loaded into context, even those unrelated to the agent's purpose. There's no way for an agent to declare which skills it needs.

Problem

• Context budget is finite. Loading irrelevant skill descriptions wastes tokens.
• Auto-invocation noise: The model may consider skills irrelevant to the agent's domain.
• Plugin authors building multi-domain plugins (SRE + backend + frontend) can't scope skills per agent.

OpenCode already supports per-agent tool permissions (allow/deny/ask with wildcards), which is great. But this doesn't extend to skill loading — all discovered skills are loaded into context regardless of which agent is active.

Proposed solution

Allow agents to declare which skills they need via a skills field in their frontmatter:

# .opencode/agents/sre.md
---
description: "SRE agent for incident response and infrastructure tasks"
skills: ["sre-runbook", "kubernetes", "incident-response"]
---

You are an SRE agent...

# .opencode/agents/backend-developer.md
---
description: "Backend development agent"
skills: ["api-scaffold", "db-migration", "code-review"]
---

You are a backend development agent...

Behavior:

• Agent with skills: [...] → only loads descriptions for those skills
• Agent without skills field → current behavior (loads all)
• Skills not in the list are not loaded and cannot be invoked

Alternative — skill tags:

# Agent
---
skill-tags: ["sre", "infra"]
---

# Skill
---
name: sre-runbook
tags: ["sre"]
---

Use case

Multi-domain engineering plugins with agents and skills for different domains. When an SRE agent is active, backend scaffolding skills shouldn't consume context. Today all skills load regardless of the active agent.