{"version":"2.1.248","anchor":"workflow-authoring-skill-autoloads-and-gates-the-workflow-to","canonical_anchor":"workflow-authoring-skill-autoloads-and-gates-the-workflow-to","heading":"Workflow-authoring skill autoloads and gates the Workflow tool","tier":"notice","area":"Workflows","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248\/e\/workflow-authoring-skill-autoloads-and-gates-the-workflow-to","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248","markdown":"### Workflow-authoring skill autoloads and gates the Workflow tool\n\nA bundled workflow-authoring skill loads itself when you mention workflows, and multi-agent runs need your ask.\n\n**What**\n\nClaude Code now ships a bundled `workflow-authoring` skill that is registered at startup alongside cowork-setup, loop, schedule-remote-agents, claude-api and claude-code, and pulls itself into a turn when you mention a workflow keyword or enter ultracode with a full reminder. Script-writing guidance now tells the model to load it before writing a script, and the Workflow tool's own instructions open with a hard rule that multi-agent orchestration only runs when you asked for it. Together this means workflows are written with real guidance in context, and are not started behind your back.\n\n**Details**\n\n- The Workflow tool may only be called after an explicit opt-in: the keyword \"ultracode\", session-level Ultracode, an explicit request in your own words, a skill or slash command that says to, or a named saved workflow; otherwise the model is told to use the Agent tool, or to estimate the cost and ask you first.\n- The tool description embeds a canonical `pipeline()`\/`parallel()` example and requires a plain literal `export const meta = {...}`.\n- The skill is unavailable when the entrypoint is `local-agent`, when `skillOverrides` sets `workflow-authoring` to `off` or `user-invocable-only`, or when a configured skill allow-list excludes it; the Workflow tool then falls back to a shorter description.\n- Availability is computed once and cached for the session, so changing the override mid-session has no effect until you restart.\n- Each autoload fires the `tengu_workflow_authoring_skill_autoload` event with `trigger` set to keyword or ultracode.\n- Unlike the API and Code skills, which have `CLAUDE_CODE_DISABLE_CLAUDE_API_SKILL` and `CLAUDE_CODE_DISABLE_CLAUDE_CODE_SKILL`, there is no environment variable to disable this one; the skill override is the only switch.\n\n**Evidence**\n\n`workflow-authoring`, `registerWorkflowAuthoringSkill`, `tengu_workflow_authoring_skill_autoload`, `ONLY call this tool when the user has explicitly opted into multi-agent orchestration.`\n\n- Area: Workflows\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 4\/5"}