{"version":"2.1.248","anchor":"skill-results-describe-read-only-loading-and-background-sub-","canonical_anchor":"skill-results-describe-read-only-loading-and-background-sub-","heading":"Skill results describe read-only loading and background sub-agents","tier":"internal","area":"Skills","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248\/e\/skill-results-describe-read-only-loading-and-background-sub-","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248","markdown":"### Skill results describe read-only loading and background sub-agents\n\nSkill results now say when instructions were only loaded, or when a background sub-agent was launched.\n\n**What**\n\nThe Skill tool's result schema now spells out two shapes: an inline result that can carry `readOnly`, meaning the skill instructions were loaded without executing anything, and a forked result carrying an agent id plus `background`, meaning a sub-agent was launched and its real outcome arrives later as a task notification.\n\n**Details**\n\n- The input schema tells the model to use a name from the available-skills list and not to guess.\n\n**Evidence**\n\n`The name of a skill from the available-skills list. Do not guess names.`\n\n- Area: Skills\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 3\/5"}