by GhalebDweikat · Claude Skill · ★ 112
winnow A calibrated context sieve for Claude Code. Every large , , or result is judged before it enters Claude's context. Blocks the judge is confident you don't need are replaced with a three-line stub: what was hidden, a one-paragraph summary from a cheap model, and a key that restores the full text on demand. Nothing is lost; it just stops costing tokens until you ask for it. Terms used below. The judge is the model that answers one yes/no question per block ("is this block needed for the current task?") with a probability.
| Stars | 112 |
| Forks | 14 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 72.9146377608921/100 |
| Open Issues | 2 |
| Last Updated | 2026-10-06 |
| Created | 2026-09-16 |
| Platforms | claude-code, python |
| Est. Tokens | ~19k |
These tools work well together with winnow for enhanced workflows:
Explore other popular claude skill tools:
winnow is A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.. It is categorized as a Claude Skill with 112 GitHub stars.
winnow is primarily written in Python. It covers topics such as claude-code, claude-code-plugin, context-management.
You can find installation instructions and usage details in the winnow GitHub repository at github.com/GhalebDweikat/winnow. The project has 112 stars and 14 forks, indicating an active community.
winnow is released under the MIT license, making it free to use and modify according to the license terms.