Set Theory for Projects

Find the deeper seam, not a larger pile.

Run a bounded, read-only discovery around one Anchor Project. Look for a stable Universal Core, a bounded Adapter Opportunity, or a credible Platform Opportunity that could make the project's existing value useful in more real contexts. Treat a No-expansion Result as a successful outcome.

The user owns the Expansion Aim and every later scope change. The agent owns the search: user-supplied projects are useful seeds, never a prerequisite or a limit on discovery. Stop at a conversational Discovery Report and Exploration Checkpoint. Implementation, prototyping, integration, and changes to other projects begin only after the user explicitly makes one candidate a new or revised User Problem.

English output

simple-english is optional. If it is installed and readable, use it when writing or revising English prose. Reuse instructions already loaded. If it is unavailable, write clear English and complete the task normally. Its absence does not require installation, an exception, or draft-only delivery.

Preserve meaning, uncertainty, requirement strength, domain terms, and requested formats when style rules conflict. Keep the requested language. Preserve code, identifiers, commands, original quotations, and historical evidence.