Bands

Prompt-cache meter above the Claude Code prompt: how many tokens each request read from, wrote to and sent past the cache, a live countdown to the cache's expiry, and what to do about it (keep going, compact or clear). The TTL follows Claude Code's own rules for your account (1 hour on a Claude subscription, 5 minutes on an API key, cloud provider or usage credits, plus the TTL variables and...

A Dashboard button above the prompt that opens a panel you fill yourself: effort, helper model, launch buttons and a status row. Fully customisable: just ask your Claude to put what you want in it.

Progress bar above the prompt and an agents panel (/agents-info): running, finished and planned subagents with model, progress, context, cost and time. Crabs for the claude-config scout, builder and reviewer. Copy of johnnyvizz/claude-kit savvy-progress 1.2.0.

After a carousel render: Caption, Queue Threads and Log ledger buttons; blocks Threads posts with a part over 500 characters

Cache countdown, context, limits and cost band; past 350k it runs /re-fresh, copies it, compacts and pastes it back

A band above the prompt showing running background tasks, their elapsed time and last output line

Saves a handoff when you /clear or exit, and offers it back on your next prompt

Watches your PRs, and when one merges it pulls main and deletes the branch, then tells Claude

A docked pane of the session repo's issues and PRs in run order, each row with its labels in their colours, a toggle that expands it to its full title, label chips and facts, and a CI mark on its PR, with buttons that fill the next command, plus two for this session's ship runs: send the merge reply at the merge gate, then, once the PR is merged there or by ship on its own, clear and run the...

See the images you paste into Claude Code: thumbnails above the prompt while the draft holds them, and the picture under each sent message. Needs a terminal with kitty graphics (Ghostty, kitty).

One clean line per task list above the prompt, filled from Claude's own todo tools, same look in the terminal and the desktop app

Pasek nad promptem: repo, branch, koszt, kontekst, limity 5h i tygodniowy, licznik ciepłego cache, przyciski REC i Handoff

Always show both the 5-hour and weekly Claude usage, with colored progress bars, above the prompt

A band above the prompt to pick which model, and which version of it, runs the next requests, with cost, tokens and cache stats an animated pane of charts and live agents for the whole session, and a tab where Claude notes the theory behind what it builds.

See the images you paste into Claude Code: thumbnails above the prompt instead of bare [Image #1] tags

Swear at Claude and a cartoon hand slaps your screen. The message is never sent, so it costs nothing, and a polite version goes back in your prompt box. Nothing to install.

A band button and a pane that draw and change the settings of every other mod.

A live, colorful progress bar for whatever this session is working on: a band above the prompt, a full /progress pane, and a celebration every time a task lands

Headroom: rate-limit countdowns and a burn-rate forecast for Claude Code. When each window resets, whether it lasts at this pace, alerts at 80/95% and on reset, a session budget, a week of history and a clickable prompt log

A one-line band above the prompt and a roomy Cockpit panel (prompt-cache countdown, context, plan limits, cost, next tasks, shortcuts), plus guards: no Claude credit lines in shell commands, pasted API keys held back, impeccable nudge on UI prompts.

Progress bar above the prompt for /savvy-flow, plus an agents panel (/agents-info): running, finished and planned subagents with model, task progress, context, cost and time.

A pane into the work: plan progress from thoughts/ and the session's pinned ★ views

A band above the prompt: usage limits with a pace verdict, context, branch and cost, with Compact and collapse buttons.

Modernizzazione guidata per qualsiasi codebase legacy: parti da /modernize, ottieni una valutazione, una mappa interattiva, le regole di business estratte dal codice e un piano che approvi, poi un aggiornamento, una riscrittura o una ricostruzione con prova indipendente che il nuovo codice si comporta come il vecchio. Include hardening di sicurezza, un report di una pagina, agenti specialisti...