All mods

Session modes that are enforced, not requested: investigate, draft, build, ship. Denies the tool calls a stance rules out, auto-switches on phrases like "no code", and shows a pixel-art class badge above the prompt.

Merged is not deployed: follow a merged PR or commit through its workflow runs, deployments and an optional live URL with gh, on a pixel-art level map, and wake the session once when it is live or a stage fails.

Rules that are enforced, not remembered: deny, ask, rewrite or note on any tool call, subagents included. A pixel-art trap for every mistake you already wrote down.

Shows the running Claude sessions on this machine above the prompt

Rings above the prompt for limits, context, todos, tokens, cost and the prompt cache

A live Vikunja pane for Claude Code: the Doing, Blocked and To-Do lanes, the task the session is working on, and a button to start a session on a task in its folder

Usage bar above the prompt (context, rate limits, cost, tokens) and a Workbranch pane: trial copies of your project you can save, bring into main or throw away. Italian and English.

A two-row band above the prompt: context, prompt cache countdown and hit rate, rate limits with reset times, git

Audit trail of skill invocations and file changes for Claude Code and Codex sessions

An animated pixel-art Claude mascot above your prompt, with a theme of the day picked by Claude itself / Une mascotte Claude animée en pixel art au-dessus du prompt, avec un thème du jour choisi par Claude

Instant commands that run without a Claude turn: /build-status for the latest xcodebuild, /wt for the worktree list

Refuses force-pushes, and before a git command that would destroy work that isn't Claude's own, shows an alarm with what would be lost and asks

Saves every conversation to a per-project SQLite memory and lets Claude search it

输入框下方的原生 HUD：模型、路径、git/worktree、上下文、5h/7d 用量与重置倒计时、输出速度、缓存命中率

Asks a local Clef decision model whether an expensive tool call or subagent is actually needed before Claude Code pays for it. Logs every decision; shadow mode by default.

Shows Claude's latest thinking block above the prompt while a turn runs

Picks the Claude model and reasoning effort for each turn with Cloudflare Clef, a fast decision model, on Workers AI or fully local (llama-server, Ollama).

Shows images pasted into the prompt as thumbnails above it

Bar above the prompt: context fill, session cost and plan limits, with a warning before compaction.

Registry of background processes and subagents: /procs command, Processes panel, counter in the status line.

Bar above the prompt: how much of your plan limit is left (5 hours and week) and when it resets.

Live cricket commentary for Claude Code: every tool call is a ball, with a scoreboard, a pixel big screen, crowd sounds and an Indian commentator who speaks.

Countdown of the 1 hour prompt-cache window, counted from the last reply.

A bar above the prompt showing current activity, 5-hour limit, weekly limit and context window.