Cut Claude Code token use by removing unused skills
Claude Code can include many skill descriptions in its context, and those descriptions can take up a large part of the prompt. Keeping unused skill descriptions in every run increases token use and can make the workflow less efficient. skillreaper checks Claude Code transcripts and finds skills that were never invoked. Removing those unused skills from the setup can shrink the context and reduce token consumption. The workflow is repeatable and can be combined with other optimization methods. It is most useful for intermediate or advanced Claude Code users who already rely on many skills.
Key points
- Claude Code skill descriptions can add extra context and increase token use.
- skillreaper analyzes Claude Code transcripts to find skills that were never invoked.
- Removing unused skills can reduce context size and token consumption.
- The workflow is aimed at users who already manage several Claude Code skills.
- Rare but important skills should not be removed only because they did not appear in a small sample.
Quick term guide
- context
- The information an AI uses to understand your request, such as files, notes, and past messages.
- workflow
- A repeatable set of steps for getting a task done.
- transcripts
- Records of the messages and actions from a session with an AI tool.
- transcript
- A full written record of everything spoken in a video
- maintenance
- The ongoing work of fixing, updating, and supporting something after it is built.
- automation
- A way to make repeated work happen without doing every step by hand.
- Claude Code skill
- A set of custom instructions added to Claude Code that teaches it to follow a specific workflow or set of rules for a project.
- Claude Code skills
- Rule sets that guide how Claude Code works on certain tasks.