After each ask you type, says what it looked like it needed and what it cost; after a simple or routine ask on a bigger model or effort than it needed, what Haiku, Sonnet or a lower effort would have cost; warns when an ask runs on too small a model or a complex one at low effort; says when the context has grown expensive and how to shrink it; ships /model-fit:baton, a handoff note for a fresh session. Optional Jev shadow labels for comparison.
1 skill
Asks one to three questions about what this session changed, one at a time, and checks your answers against the code.
1 skill
Notices snags that come back across sessions (search spirals, fix loops, large tool outputs) and offers one change to the environment that stops them.
Lists the plugins, skills and MCP servers you have not used lately and that cost tokens every turn (/unused), judged by Claude Code's own counters, and disables or removes them from a pane.
Flags a turn that wrote a lot and offers a /guide reading order; before Claude commits, measures the change's blast radius and asks Jev about risk and readability, then lets it through, flags it, or holds it for review.