标签：token-efficiency

A fuzzy linter for coding agents. It checks the code your agent writes against your team's best practices while the agent is still working, not at code review.

Screening LLM agent tool output for relevance and prompt injection with Jev, a hosted System One classifier. Harness, test beds, run records and analysis.

Agent Skill that offloads bulk yes/no, pick-one-option and rating judgments to TypeSafe's Jev so Claude spends fewer tokens during investigations.