Skill

largest-first-context-shedding

When a single API-level user message trips the per-message tool-result budget, drop the largest fresh results first so the model still receives the frozen context at the tightest budget point.

Claim this listing

Connect your GitHub to prove you own or maintain this listing. We verify repo access automatically — most publishers are confirmed in seconds.

1Connect GitHub

2Submit your claim

3Auto-verified, or reviewed within 48h