Prompt
596 mods. Bands above the prompt and tools that rewrite what you send.
- fuel 0.2.0 Above the prompt only when you are near a limit: context window, plan limits with reset countdowns and an estimated cache age, as clay-to-red gradient gauges; a Compact button; /fuel any time for a one-line summary 0
- pulse 0.1.0 A slim glowing bar above the prompt that shows what Claude is doing: breathing when idle, a wave while thinking, a flow in the tool's colour while a tool runs, a green sweep when done, a red pulse on an error; /pulse and /pulse off 0
- context-bar 0.3.1 Context fill as a bar above the prompt, with prompt-cache hit rate and whether the cache is still warm 0
- prompt-booster 0.1.0 Adds repo context to short prompts, plus one-word commands for common tasks. 0
- pixel-pet 0.1.0 An animated pixel-art companion above your prompt that reacts to your session and your typing, with a live context meter. 0
- prompt-band 0.1.0 Draw hook-notices' and turn-nav's lines above the prompt as one row. 0
- run-cat 0.1.0 Claude が考えている間、CLI のプロンプト下のヒント行で AA の猫が走る(端末だけで描く) 0
- pixel-parade 1.0.0 Hand-drawn pixel-art cats and dogs wander above the prompt: they stroll, sit, nap, zoom, share hearts and chase each other. Choose how many, and cats, dogs or both. 0
- typing-combo 1.0.0 A fighting-game combo counter above the prompt: big digits that hit harder the faster you type, with hit-stop, ranks, keys per second and your best. 0
- cache-tax-plus 1.0.0 Stoppt eine teure Nachricht an einen kalten Prompt-Cache einmal und zeigt vorher den Preis. /keepwarm hält den Cache in Pausen warm (kostet Tokens). 0
- bgjobs 0.1.0 Pane listing processes started by Claude sessions, orphans included 0
- cache-tax 2.2.1 A Claude Code mod that keeps the one-hour prompt cache warm during breaks and stops a cold send once with its estimated rewrite cost. Warming uses model requests and costs tokens. Requires Claude Code 2.1.287+. 0
- reflect-mod 3.3.0 claude-reflect as a Claude Code mod: a model check on each short prompt finds reusable corrections (any language); a band above the prompt saves them to CLAUDE.md on one press 0
- handily-item-toasts 0.4.0 A toast when a work item changes outside this session, at most one every 30 s. 0
- agent-cross-check 0.1.0 When another coding agent (or a person) commits to your repo, Claude notices, runs mechanical checks (line endings, secrets, .env files) and audits the commits by diff and tests instead of trusting their report. 0
- reflect-plus 1.0.0 Erkennt Korrekturen in deinen Prompts und speichert sie auf Knopfdruck als Regel in CLAUDE.md 0
- orca-split-editor 0.1.0 Orca のペインを上下に分割してエディタでプロンプトを書く 0
- suggestion-chip 0.1.0 Claude's suggested next prompt in a bar above the prompt box, sent with one click 0
- terminal-pet 1.0.0 A cat in the empty prompt box that reacts to your day, plus /pet-stats silly stats 0
- jev-route 0.2.0 Jev picks the model and the effort for each request, from how demanding it is 0
- quiet-output 1.0.0 Condensed transcript: tool calls fold into one-line notices and results are hidden; /quiet toggles full detail. 0
- idle-compact 0.1.0 Compacts the session once it is 20% full and has been idle 50 minutes, while the prompt cache is still warm. 0
- lean-context 0.2.0 Measures and, once approved, strips configured sections of the project instruction file from the Claude Code context while no spec is active for the branch. 0
- session-banner 0.1.0 Shows a plain-text logo with a gradient and one shimmer sweep above the prompt when a session starts, until the first prompt. /banner shows it again. 0
- mission 0.2.0 /mission opens a live map of the main agent, its subagents and every tool call, plus a code map of the files they touch. 0
- context-pet 0.1.0 A pet above the prompt that grows and turns red as the context fills up 0
- dashband 0.1.0 Prompt cache, context and plan limits at a glance, in the prompt footer and above the prompt 0
- prompt-enhancer 0.1.0 Rewrites a vague draft in the prompt box using the project's instructions, skills and conversation; Send submits it. 0
- boss-fight 0.1.0 Failing lint, tests or typechecks spawn a boss above the prompt; each fix damages it 0
- model-router 0.1.0 Routes prompts and subagents to a cheaper or stronger model by what they ask 0