largest-first-context-shedding

SKILLWorkflowcommunauté
v0.0.0ychampionMITMis à jour il y a 4 moisSource →

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.

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
36Étoiles du dépôt
1Clients
1Formats
il y a 4 moisDernière mise à jour
Skill
Auteurychampion
Version0.0.0
LicenceMIT
CatégorieWorkflow
Formatsskill.md
PromptNon publié
Compatibilité
Claude✓ Pris en charge
Cursor
Copilot
ChatGPT
Gemini
À propos

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.

Mots-clés
skillclaude