{"version":"2.1.238","anchor":"skill-tool-instructions-rewritten-plus-a-read-only-note-for-","canonical_anchor":"skill-tool-instructions-rewritten-plus-a-read-only-note-for-","heading":"Skill tool instructions rewritten, plus a read-only note for coordinator sessions","tier":"notice","area":"Skills","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238\/e\/skill-tool-instructions-rewritten-plus-a-read-only-note-for-","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238","markdown":"### Skill tool instructions rewritten, plus a read-only note for coordinator sessions\n\nSkills can be named with a scope like `apps\/web:deploy`, and coordinator use is read-only.\n\n**What**\n\nThe Skill tool's description was rewritten: background skills return only an agent name, skills can be named with a scope such as `apps\/web:deploy`, and an already-loaded skill block should be followed rather than invoked again. In coordinator mode an extra paragraph is appended saying the coordinator's own use is read-only, with no forking, permission grants, hooks or preamble shell commands, and that execution happens in workers.\n\n**Details**\n\n- The addendum requires `CLAUDE_CODE_COORDINATOR_MODE`, and locally also a remote or cowork context; without those the base description is used.\n\n**Evidence**\n\n`In a coordinator session, the coordinator's own use of this tool is read-only`\n\n- Area: Skills\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 4\/5"}