Repo · Coding & code review

jev-skill-gate

Gate Claude Code's skill manifest with TypeSafe Jev: score installed skills for relevance to the current work and write skillOverrides so only the…

Open github.com ↗

From the repository

Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.

agent-skillsai-agentsai-toolinganthropicclaudeclaude-codeclaude-code-hooksclicontext-engineeringcontext-managementcontext-windowcost-optimizationdeveloper-toolsjevllmllm-toolsnodejsprompt-engineeringtoken-optimizationtypesafe-ai

How builders describe it

Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.

Gate Claude Code's skill manifest with TypeSafe Jev: score installed skills for relevance to the current work and write skillOverrides so only the useful ones reach context.

Claude Code hook that scores installed skills against your prompt with Jev and writes skillOverrides so irrelevant skills stay out of context; a local TF-IDF ranker runs when no API key is set.

The decision Jev makes

Label a change, score its risk, pick the relevant file, or decide whether a coding agent should continue.

Where it fits

Code review and coding agents are full of small questions: is this change risky, what kind of fix is this, which file matters. These projects answer them with Jev and route the rest to people or bigger models. All 450 coding & code review projects →

Related projects