Results for “pa”

Run a written plan with Claude Code: each part in its own background thread, reviewed until OK, from one chat

Small, good-looking games in a side pane: /games for Snake, Tetris, Breakout, Dino Run, Pong, 2048, Minesweeper, Lights Out, Memory, Connect Four, Tic-tac-toe, Wordle and Hangman, with milestones and your progress saved

Read the files of your project in a calm pane beside the chat.

Highlight part of Claude's answer and reply to it. The text goes into your prompt as a quote.

The session's dashboard in one pane, opened by /dash: the model, the effort and presets that set both, ultracode and fast mode, each switched with one click; the context and quota gauges, the cost and the duration, /compact behind a confirmation, the session's name; the agents, commands, skills, plugins, MCP servers and hooks, a plugin or a server turned on or off from there; and the /config...

A podcast player inside Claude Code: subscribe to feeds, browse episodes in a pane, and play them with a now-playing bar above the prompt

Tracks what the AI is waiting on you to decide in the main conversation: a reminder above the prompt, and /decisions opens a pane to quote, accept or remove each item.

Forward each you-should-know heads-up to Claude, so you no longer paste it in yourself

A pane listing the open GitHub issues of the session's repository

Experiments that probe what the rendering engine accepts: SVG, animation, interaction and every element, each in its own pane

The project's dev servers from .claude/launch.json in a pane: start, stop and restart each, see which answer and read their output

A session overview pane: context, cost, time, turns, tools, files, subagents, limits and git; cells in the terminal, charts in the desktop app

Garde-fou : suspend les commandes Bash sensibles et demande Proceed / Cancel dans un panneau avant exécution.

Shows what the conversation's context holds in a side pane: files, skills, MCP servers and memory files

Pattern-based checks that deny .env reads, git force pushes and rm -rf on / or your home folder before Claude Code runs them.

/music: what macOS Music.app is playing, in one line above the prompt. A pressable play/pause glyph, track · artist · album, a progress bar with the clocks, and a pressable next-track glyph. One read of Music.app every five seconds, shared by every open session; the clock ticks in between.

A pane beside the transcript that fetches one Jira issue by key and lets you attach it to your next prompt.

A pane beside the transcript that shows the model's open interview questions and submits every pick as one prompt.

A pane beside the transcript that holds the next things to tell the agent: write blocks of text while a turn runs, then press [+] to put one block into the prompt box.

A pane beside the transcript that shows the model's newest open draft and sends your comments on it, span by span, as one prompt.

Keeps long sessions cheap and easy to pick up: warns before a session's cache goes cold and what coming back costs, nudges a wrap-up past a set size, saves a quiet session's state by itself before its cache goes cold, holds a command that keeps failing, and adds /wrapup, which also saves the session's dead ends.

Draws the area above the prompt for other mods: their blocks, packed into configurable rows

A card above the prompt in the desktop app and the terminal: how full the context window is, what fills it, and what the session has cost, in Anthropic's palette.

Session dashboard: a /tether pane for a working-on note, context, the assumptions Claude is making, the work it puts off, decisions, needs-you tasks, subagents and cost. Every section folds.