Panes

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 /model, /output-style, /fast, /effort, MCP or plugin changes and /config rows that would throw away a warm prompt cache, with the cost of rewriting it; names the rebuilds it could not prevent.

Forecasts how many turns remain until auto-compaction from smoothed per-turn context growth (tool output vs conversation), and at natural breaks offers Compact now with a focus Haiku drafts.

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.

See which tools fill the prompt, grouped by MCP server, and move them behind ToolSearch (or pin them in) per project.

OpenSpec lifecycle governance for Claude Code: stage band, fail-closed edit gate, task progress and an append-only execution log.

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.

A pane of this repo's latest GitHub Actions runs, refreshed while open

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

Holds every message Claude tries to send (WhatsApp, email, Slack) until you read it, see who it goes to, and press Send

Stops Claude reading .env and key files, masks API keys in command output, and lets you hand Claude a key through a pane without it ever seeing the value

A live usage cockpit above the prompt: context, plan limits with pace forecasts, and cost by day, week and month, in a one-line glance that expands into tabs and a dashboard pane

A side chat for Claude Code, like the desktop app's /btw. Ask follow-up questions in a pane without touching the main conversation, or call an agent with /btw @name. Independent mod, not made by Anthropic.

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

The next Muslim prayer time under Claude Code's prompt, a gentle reminder at adhan, and a pane with today's sky, the timetable, a weekly prayer tracker and the Qibla. Calculated on your machine; no network.

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.

Claude Code에서 /mud 명령으로 로컬 VibeMUD RPG를 조작하는 한국어 중심 플러그인입니다.

🔔 Closes the PR loop: watches a PR until CI and agent reviews are green, and weighs review comments before acting on them.

😤 Remembers your corrections: offers to hold a lasting preference, reminds Claude of it every session, and fixes commands it can swap safely.