Prompt

Your commit and pull request credit line, your way: Claude Code's default, none, or your own template with {model}.

Per-prompt effort autopilot: classifies each prompt (Jev, Claude Haiku, or heuristics) and sets that turn's effort, and optionally its model, only when the switch beats the prompt-cache rewrite it causes.

Asks before sending a huge pasted log, stack trace, JSON or CSV: shrink it to a digest (head, tail, error lines) and save the full text under .claude/pastes, or send it as is.

See the system prompt section by section with sizes, and switch sections off for a project.

See the reminders and notices Claude Code injects for the model, by type and size, and mute the ones you do not want.

Jev picks the tool that fits Claude's next step and Claude gets it as a hint, shown live and measured against a control group. Native to Claude Code: no gateway, no proxy.

Ends every turn with the date, time, duration and tool call count

A desktop notification with a sound when Claude finishes a long answer or may need your OK

A live panel above your prompt: the plan as a stage bar, what Claude is doing in plain English, your asks ticked off, and a sound when it is done

Find what you ask Claude again and again, then build a mod that does it for you: /mod-audit, /mod-build, /mod-check and a habit spotter

A pixel-art office in a local web page: every Claude session gets a desk, walks to the filing cabinet when it reads, types when it edits, flies paper planes when it messages, and shows a live Done-by clock

Live pane of every ask you make in a session, ticked only with proof. Ask-splitter: right after you send a prompt, a band shows "I heard 3 asks" and numbers each one

Grades every reply for length, long sentences and jargon, and offers a one-click 'Say it simpler' draft when it goes over your bar

Before Claude builds anything, it re-reads your own CLAUDE.md rules and keeps a reference's structure without copying its look

Claude never deletes a file for good: rm, find -delete and git clean move files to the Bin, with a receipt and /undo-delete

A band above the prompt listing your other open Claude Code sessions, what each one is for, and an Ask button

Opens the newest page, image or video Claude made at the end of each turn, without stealing focus

A chibi pixel witch who wanders your consoles, follows you between them, and sometimes picks fights

Session panel: context and usage limits, model, mode, agents and notifications, beside the transcript

A permanent pane: the ticket and summary of what Claude works on, its progress, and its todo list

A per-session ledger of topics, decisions, open questions, to-dos and board state, kept by Claude through a tool and shown in a pane.

A side panel for questions about the current session: it reads the conversation from cache, looks things up read-only, recaps, says what the main thread is doing, draws diagrams as artifacts and sends a note to main.

Stops secrets from leaking before they are written, printed or committed to git.

Keep unrelated topics from pulling Claude off your code: listed terms become stable placeholder names (or their lines are dropped) in tool output, prompts, CLAUDE.md and skills before the model reads them. The system prompt is never changed.