Tools & agents

POWERTRAY: a pane of things to look at or listen to (what Claude made this session, things related to what you are on, local servers), a player for a film's sound, plain-words recaps of the work (quick or detailed on request, quick ones on their own if you turn them on; flagged stale when they no longer hold), checklists Claude and you tick together (or one written from the conversation on...

Keeps review findings (H1, M3, L2...) per repo across sessions and ticks them off when their PR merges

Automatic compaction summarizes only the older part of the conversation and keeps the latest part word for word; a reopen tool brings back anything summarized, from a local archive

Claude draws Mermaid, D2 and PlantUML diagrams (UML, flowcharts, sequences, architecture) into a side pane with history, versions, export, copy and share.

Turns build, test and lint output from tsc, cargo, go, pytest, jest, gradle and more into a live pane of errors by file, and hands Claude the diagnostics instead of the raw log.

Suggests next steps after every prompt and keeps them in a to-do list by category, in a panel you can click (/todo) or drive with commands.

rook by TestMu AI inside Claude Code: Claude runs rook against the agent it is building and gets failures back grouped into root-cause clusters with rook's remedies, writes scenarios, a live pane with per-scenario lanes and openable failures, re-test prompts after agent edits, a status line score, /rook commands and a production-target guard.

One Mod status pane for Claude Code Desktop with an icon rail: Progress (live plan bars with step times and history, forked from zycck/claude-mods plan-progress), Next steps (up to three suggested next prompts; a click puts one in the composer), Skills & agents (the skills and agents called this session, each tagged personal, project, plugin or built-in, plus the rule and CLAUDE.md files...

Analysiert und optimiert Prompts und Agenten-Aufträge passend zum aktiven Modell und macht Subagenten sparsam: Lagebild, schlanke Varianten, Briefing-Gate, Fork-Sperre und Kostenanzeige.

Live plan, % done, time left and a one-line 'now' for long tasks, in a pane and on the working row.

Brings up a folder's dev stack from a YAML stack file: docker compose, detached dev servers, one-off tasks and check scripts, one pass at a time, with each service as a colored dot under the prompt

A side pane that grades every test in the project (strong, shallow, brittle, hollow, duplicate), tells Claude how to write tests that grade strong, and shows coverage.

Shows the images you paste and the ones Claude reads, receives or creates in a small strip above the prompt: PNG, JPEG, GIF, WebP, HEIC, AVIF, TIFF, BMP and SVG.

Reads Claude's last response aloud: natural edge-tts voices (free, no API key) with an offline fallback to the OS voice, plus pause and stop buttons.

A pane beside the conversation that shows the steps Claude plans and keeps them current as it works

Side pane of open decisions, todos and links for the current session

A side pane in Claude Code that draws mermaid diagrams as colored text art, with C4-style zoom: click a box to see the level inside it

Turns a session into an orchestrator that delegates work to haiku and sonnet subagents, keeps its own context small, sizes each task to about 150K tokens of subagent context, and lists the running and past agents in an expandable band (/orchestrator on|off|status)

Context usage, branch and tool count in a band; tokens per request charted in a pane; a note tool for Claude and a check before dangerous commands. English and Japanese

Opus 5.5 conducts a mission: plans sized tasks, delegates hard labor to Sonnet 5.5 workers and narrow jobs to Haiku 5.5 scouts at the reasoning effort each task needs, and shows every agent, what it is doing and the mission's % in a live pane

Viser, hvor meget af dine grænser (5 timer og ugen) dine samtaler bruger, også planlagte opgaver og forbrug i chat og Cowork, med indsigt på tværs af samtaler, råd til at bruge færre tokens og bedre første prompts

Session dashboard: a live stats bar above the prompt and a /desk pane for context, cache, subagents, cost, the assumptions Claude is making and the work it puts off.

Renders each .dgmo file Claude writes or edits in a live side pane, and tells Claude the parser's errors

HUD completo (modelo, projeto, git, contexto, uso, ferramentas, agentes, todos, alertas, orçamento, histórico, resumo, painel de detalhes e temas) mais a linha do synapse: clima/previsão, % do contexto, tamanho em MB do contexto/anexos, tokens e gráfico dos últimos turnos.