{"version":"2.1.238","anchor":"preloading-a-skill-no-longer-does-the-built-in-command-s-rea","canonical_anchor":"preloading-a-skill-no-longer-does-the-built-in-command-s-rea","heading":"Preloading a skill no longer does the built-in command's real work","tier":"notice","area":"Skills","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238\/e\/preloading-a-skill-no-longer-does-the-built-in-command-s-rea","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238","markdown":"### Preloading a skill no longer does the built-in command's real work\n\nPreloading a skill no longer runs the expensive work of codebase analysis or `\/insights`.\n\n**What**\n\nTwo built-in commands now detect that they are being loaded as part of a skill preload and skip their work: the codebase-analysis prompt skips its expensive preparation, and `\/insights` returns a placeholder instead of generating a report. The report is still produced normally when you run `\/insights` yourself.\n\n**Details**\n\n- Both branch on the existing skill-preload and read-only-load options rather than a new flag.\n- The tool-result formatter gained a matching read-only branch that tells the model nothing was executed.\n\n**Evidence**\n\n`The \/insights report is generated only when the command is invoked directly.`\n\n- Area: Skills\n- Names: `\/insights`\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}