ruleprof is an open-source CLI tool that helps AI agent developers analyze and ablate their CLAUDE.md or AGENTS.md rules to see which ones actually change agent behavior and which only increase token usage. It provides actionable insights for optimizing agent configurations and reducing unnecessary costs.
In the Agent evaluation & testing space, ruleprof takes a focused approach. It focuses on determining which agent rules meaningfully impact LLM agent behavior versus those that only increase token costs. ruleprof is an open-source project aimed at AI agent developers. The project is open source (MIT). ruleprof is available on the command line.
fernforge builds and maintains ruleprof, and it first shipped in 2026. The project is developed in the open on GitHub with 7 commits in the last 90 days. Key capabilities include rule ablation, token usage analysis, and agent behavior profiling.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match