Status line

Stops accidental truncation of real code: no "// ... rest of the code" placeholders over real code, and a question before a Write or Edit throws away most of a file.

Supply-chain check before installs: npm/pnpm/yarn/bun/npx, pip/uv/poetry/pipx, cargo and gem packages are looked up first; nonexistent names are refused, brand-new, unpopular, deprecated or lookalike ones need your yes.

Protected files and a project boundary: Claude can't edit .env, keys or .git, asks before touching lockfiles and migrations, and asks before writing outside the project.

Keeps credentials out of your code, your shell commands and Claude's context: blocks hard-coded secrets in edits, asks before commands with literal keys, redacts secrets from tool results and flags them in prompts.

Prompt-cache hit rate, a live warm/cold countdown, cache-bust alerts with likely causes, savings, and optional keep-warm pings.

Context-window gauge: a fill bar in the status line, toasts as it fills, a /ctx breakdown pane with Compact now, and optional auto-compaction between turns.

Spend tracking across sessions: session and today's cost in the status line, daily and weekly budgets with toasts and an optional hard stop, and a /spend pane.

One compact status line: model, context fill, cache hit and warm countdown, session cost, the fullest rate limit, and git branch with changed files.

Subscription rate limits at a glance: each window and its reset in the status line, toasts at 75% and 90% and when your pace beats the reset, and a /limits pane.

Tool latency: times every tool call, shows a live timer for slow ones, and a /stopwatch pane with per-tool averages, p95, max and the slowest calls.

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.

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

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

Shows the main model, how many agents use each model (and how many are live), and warns about agent crowds and huge contexts

Keeps the 5-hour and weekly limit windows, their burn rate, a run-out projection, context fill and session cost pinned under the prompt

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

A fuel gauge above the prompt: how much of your Claude plan is left, and when it refills.

An oil gauge above the prompt: this week's Fable use, beside Gas Gauge.

Plain-language replies when you ask for them. Say "layman", "I'm lost" or "explain again" and the next reply uses everyday words, one idea, one real example. Ask twice and plain mode stays on for the session; /layman on|off switches it by hand.

Zsemle, a pixel-art companion above the prompt (golden retriever, cat, slime, paperclip): watches every usage limit (50/75/90% warnings, pace forecast, resets, API errors, automatic model switch and compaction, cost), stops work at 95%, guards file writes and cheers long turns. English and Hungarian, terminal and desktop.