feat: add native skill tool with permission system

[malhashemi]

Summary

• Add native skill tool for on-demand skill loading with pattern-based access control
• Support agent-specific permission overrides for fine-grained skill access

Features

Skill Tool

Skills are now loaded on-demand via the native skill tool. The agent sees available skills listed in <available_skills> and can load the full content when needed:

skill({ id: "pr-review" })
skill({ id: "prompter/skill-creator" })  // nested skills use path-based IDs

Skill Permissions

Control which skills agents can access using pattern-based permissions in opencode.json:

{
  "permission": {
    "skill": {
      "pr-review": "allow",
      "internal/*": "deny",
      "experimental/*": "ask",
      "*": "allow"
    }
  }
}

Permission	Behavior
allow	Skill loads immediately
deny	Skill hidden from agent, access rejected
ask	User prompted for approval before loading

Patterns support wildcards: category/* matches all skills in that category.

Agent-Specific Overrides

Override global permissions for specific agents. Useful for giving specialized agents access to restricted skills.

For custom agents (in agent frontmatter):

---
permission:
  skill:
    "document-skills/*": "allow"  # override global deny
---

For built-in agents (in opencode.json):

{
  "agent": {
    "plan": {
      "permission": {
        "skill": {
          "internal/*": "allow"
        }
      }
    }
  }
}

Disabling the Skill Tool

Completely disable the skill tool for agents that shouldn't use skills:

For custom agents:

---
tools:
  skill: false
---

For built-in agents:

{
  "agent": {
    "plan": {
      "tools": {
        "skill": false
      }
    }
  }
}

When disabled, the <available_skills> section is omitted from the system prompt entirely.

Nested Skills

Skills can be organized in subdirectories. The skill ID is derived from the path:

.opencode/skill/
├── pr-review/SKILL.md          → id: "pr-review"
├── prompter/
│   ├── agent-creator/SKILL.md  → id: "prompter/agent-creator"
│   └── skill-creator/SKILL.md  → id: "prompter/skill-creator"
└── docs/
    └── api-guide/SKILL.md      → id: "docs/api-guide"

---

Note: Skill tool responses are whitelisted from session compaction pruning to ensure loaded skill content remains available throughout the conversation.