Results for “pa”

A pane showing the main loop and every subagent of the session as pixel crabs, each under its role's hat: a short name, role, model, plan progress, context fill, tokens, estimated cost and time, with totals on top and the finished ones kept below; while agents work, one line above the prompt says how the run stands.

A pane for finding and reading files without asking the model: an explorer with search by name that lights up the files Claude reads, writes and commits as it works and can follow it into closed folders, a search inside the files, git's changes since the last commit or against main with a diff of each, the type checker's errors, and a switch to another repository's folder.

Records the file edits of the last turn and steps through them as diffs in a pane.

Fold this session's hook messages into one line above the prompt; open them in a scrollable pane.

Lists your prompts in a pane and jumps the transcript to a selected prompt.

開いている PR と CI の状態を gh で定期的に取り、ステータス行とペインに出す

Plan limits, time-to-limit pace, session cost, tokens, cache hit rate, context and model in the band above the prompt

A pane of every subagent in the session: model, effort, context, tokens, estimated cost and time, with a crab per agent role on desktop. Works with any agent type or workflow.

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.

Claude FM player: a pane drawn like the stream with the current track, /lofi, volume, a mini video window; audio via yt-dlp + ffplay

Pauses risky shell commands and edits that match your patterns and asks you to proceed or cancel with buttons.

Read-only view of every user and assistant message in the current session, with collapsible tool-call details and paged loading. Open with /history.

AbovePrompt band (auto-shows the edit count) + Pane (file-grouped list with [Revert]). Click the band's [View] (or /file-history) to open the Pane and revert.

A tiny pixel-art platformer in a side pane: three worlds of running, jumping, stomping and coins. /play

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.

A side pane that lists subagent runs and chosen shell commands with their state and elapsed time.

One line above the prompt: context tokens, session cost, active time, a prompt-cache countdown and your plan limits with pace

Live panel showing this session's context, token and cost usage

After each turn, suggests up to three next prompts: above the input in the terminal, behind a 💡 chip in the footer of Claude Code Desktop that opens a numbered Next steps pane. Press 1, 2 or 3 (or click one) to put it in the prompt box as a draft you can edit; in the terminal 0 dismisses.

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...

A right-side pane showing, live, which files Claude is reading, editing and committing. No model calls; history kept across sessions.

Explains the X Factor kit: a one-time welcome above the prompt and /kit, a pane listing what each mod does and how to use it.

A pane that lists the files that differ from HEAD, as git diff shows them, untracked files left out

A pane that shows the GitHub checks of the current branch's pull request