Prompt

Routes each turn's reasoning effort with TypeSafe's Jev decision model, keeping the prompt cache (Claude Code 2.1.280+). Model routing is available but off by default and refused above maxSwitchTokens, since a model switch re-writes the whole context.

A shark fin cruises above the prompt while Claude works, with ctx / 5h / 7d quota and ctx-handoff's auto handoff built in

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

OS 한글 입력기 없이 Claude Code 프롬프트에서 두벌식·세벌식 390·세벌식 최종으로 한글을 친다

Surf (surfd.net) in your browser while Claude is thinking. Get pinged the moment it's done.

A fuse above the prompt that burns down with the prompt cache, with context and rate limit meters and buttons to keep the cache warm or compact

/q holds prompts until the running turn ends and sends them one per turn; a band above the prompt lists, edits, reorders and pauses them

Keeps the prompt cache of an idle Claude Code session warm: just before the cache lapses it submits a short service prompt, so your next message reads the context from the cache instead of writing it again. Off by default; /keepwarm on|off|status. Needs function hooks (early access).

/cockpit: shell commands, skills, edited files, model, context and 5h / weekly limits

Token Run: a terminal runner game inside Claude Code. The Claude mascot jumps cacti and collects coins before its tokens run out.

Flag a project for prototype mode: no git worktrees, iterate and commit directly on the current branch (main included). Works for background jobs too.

A life coach that lives in Claude Code: notices your work rhythm, nudges at natural pauses, keeps small commitments, and coaches with Claude. Global evidence library plus a China pack. All data stays on your machine.

Picks the Claude model and reasoning effort for each turn with Cloudflare Clef, a fast decision model on Workers AI.

After each turn, suggests three next prompts above the prompt box. Type 1, 2 or 3 (or click) to send one. Uses a small Haiku call per turn.

When you approve a plan, saves it as .claude/tickets/ /plan.md in the project and points Claude at that copy.

When a prompt names an earlier session's ID, attaches a digest of that session (prompts, files, commits, last reply) for Claude.

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.

ShellTime statusline for Claude Code: git, model, session and daily cost, quota, agent time and context, in the terminal and the desktop app.

Shows above the prompt how long the cache stays warm, what each message costs on your Claude plan, and one habit that saves usage

When a prompt uses architecture or design words, asks Claude to answer with the system architecture as a box-drawing tree.

Grammar fixes for prompts you type or dictate: optional auto-fix on send (LanguageTool rules or a light Haiku fix), Haiku drafts that know your project's terms, and word tools (your language to English, synonyms).

A live map of your Claude Code session: a git-style flow chart, a live feed of every tool call, a drag-and-drop task board, async grill questions, agent chat, stats and recap, in a pane you can steer from.

No claims without evidence: flags "tests pass", "CI green" and "verified" claims that nothing in the turn backs up.

Auto-continue after a turn dies on a network or API error: a pixel-art CONTINUE? countdown with backoff and 3 lives per hour.