keeper-evaluationlisted

# Keeper Evaluation Rank keeper candidates by **surplus value**: what the player is worth minus what keeping them costs. A good keeper is one priced below market, not simply the best player on the roster. ## Step 1: Load context Read `leagues.md` from the project root first — the fields that matter here are keeper rules (how many, cost mechanism, escalation), teams, scoring, and starting slots. If the file is missing or keeper rules aren't recorded, ask: How many keepers? What does keeping a player cost (a draft round, an auction dollar amount)? Does the cost escalate year over year? Then offer to save the answers back to `leagues.md`. If more than one league is defined, use the one marked `(default)` unless the user names another. ## Step 2: Gather candidates and price them For each candidate: player, keeper cost (round or $), and current ADP or auction market value. For round-cost leagues, get the **exact pick the keep consumes**: draft slot, round, and the league's collision rule if multiple keepers map to the same round. If the league has eligibility restrictions (tenure limits, drafted-only, no first-rounders, tag deadlines, etc.), screen those out before doing surplus math. Ask the user to supply these, or — if browser automation is available and they're logged in — read current values off their platform or a rankings site, stating the source and date. **Reading data with computer use.** If browser automation is available (Claude in Chrome or equivalent) and the u