{"version":"2.1.248","anchor":"a-set-of-usage-analysis-prompts-sits-in-the-build-with-no-vi","canonical_anchor":"a-set-of-usage-analysis-prompts-sits-in-the-build-with-no-vi","heading":"A set of usage-analysis prompts sits in the build with no visible entry point","tier":"soon","area":"Usage Insights","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248\/e\/a-set-of-usage-analysis-prompts-sits-in-the-build-with-no-vi","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248","markdown":"### A set of usage-analysis prompts sits in the build with no visible entry point\n\nSeven prompts that analyse your Claude Code usage habits ship with no entry point.\n\n**What**\n\nSeven prompts that analyse how you have been using Claude Code ship as plain data: project areas, interaction style, what works, friction analysis, suggestions, on the horizon and a fun ending. Each allows 8192 tokens and demands a strict JSON reply. The suggestions prompt describes MCP servers, custom skills, hooks, headless mode and task agents, and asks the model to prioritise CLAUDE.md additions you have repeated across sessions.\n\n**Details**\n\n- The list splices in an empty array before the closing prompt, which is what a conditionally compiled section looks like when it is switched off.\n- Nothing in this group shows what surfaces these prompts.\n\n**Evidence**\n\n`Include 3 opportunities. Think BIG - autonomous workflows, parallel agents, iterating against tests.`\n\n- Area: Usage Insights\n- Tier: Nothing to try yet\n- Useful: 3\/5\n- Signal: 5\/5\n- Present in the build but not switched on"}