{"version":"2.1.238","anchor":"read-only-skill-loads-tell-the-model-to-hand-execution-to-a-","canonical_anchor":"read-only-skill-loads-tell-the-model-to-hand-execution-to-a-","heading":"Read-only skill loads tell the model to hand execution to a worker","tier":"notice","area":"Skills","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238\/e\/read-only-skill-loads-tell-the-model-to-hand-execution-to-a-","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238","markdown":"### Read-only skill loads tell the model to hand execution to a worker\n\nRead-only skill loads now return a note saying nothing ran and a worker should execute it.\n\n**What**\n\nWhen a skill is loaded read-only, the tool result is now an explicit note that the instructions were loaded, nothing ran, and execution should be delegated to a worker, instead of the usual result payload.\n\n**Details**\n\n- Emitted from the read-only branch of the tool-result formatter, driven by the `readOnly` flag on the load result.\n\n**Evidence**\n\n`Nothing was executed; delegate execution to a worker.`\n\n- Area: Skills\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 4\/5"}