Skip to content
claudemods

Claude Code Slash Command Mods

Claude Code slash command mods add commands like /tally that answer instantly in code, with no model call, or change how built-in commands behave.

After running in Claude CodeFeatured

After

A prompt queue for Claude Code: /after runs your next task when the current one ends, without steering it.

  • above-prompt
  • pane
  • toast
  • status
  • Calls the model (uses your quota)
  • Reads your prompts
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.303

>_ assumption-tracker

Assumption Tracker

Log claims with /assume, then confirm or refute each one with written evidence; the history is kept per session.

  • none
  • Reads files
  • Runs commands
  • Intercepts tool calls
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.307

>_ bilingual-view

Bilingual View

Write Claude Code prompts in Chinese, send English, and read replies in Chinese through your own translation API.

  • above-prompt
  • pane
  • transcript
  • Reads files
  • Writes files
  • Runs commands
  • Network
  • Intercepts tool calls
  • Reads your prompts
  • Changes the UI
  • Adds commands/tools

tested with v2.1.310

Cache Keeper running in Claude CodeFeatured

Cache Keeper

Shows if your Claude Code prompt cache is warm or cold, keeps big chats warm and asks before a costly cold send.

  • above-prompt
  • pane
  • toast
  • Reads files
  • Writes files
  • Calls the model (uses your quota)
  • Intercepts tool calls
  • Reads your prompts
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.310

cc-arcade Games Above the Prompt running in Claude CodeFeatured

cc-arcade Games Above the Prompt

Snake, Tetris, Doom, 2048 and more games above the Claude Code prompt, plus a pet fed by Claude's work.

  • above-prompt
  • toast
  • Intercepts tool calls
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.291

>_ cc-intelligent-ui

Intelligent UI

Claude's answers drawn as typeset pictures in the terminal: tables, LaTeX math, charts and diagrams, via Typst.

  • transcript
  • above-prompt
  • pane
  • toast
  • Reads files
  • Writes files
  • Runs commands
  • Network
  • Intercepts tool calls
  • Reads your prompts
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.310

>_ clawd-actor

Clawd Actor

Clawd, Claude Code's mascot, acts out the spinner word and the running tool on a small stage above the prompt.

  • above-prompt
  • toast
  • Reads files
  • Network
  • Calls the model (uses your quota)
  • Intercepts tool calls
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.310

Tool Call Counter running in Claude CodeFeatured

Tool Call Counter

Counts Claude's tool calls per turn and session, shows the count by the spinner, and adds /tally for a breakdown.

  • spinner
  • transcript
  • status
  • Intercepts tool calls
  • Changes the UI
  • Adds commands/tools

tested with v2.1.310

>_ command-shelf

Command Shelf

Keeps successful Bash commands in a per-project shelf and replays a chosen one through normal permissions.

  • none
  • Intercepts tool calls
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.310

Context Inspector running in Claude CodeFeatured

Context Inspector

Shows what fills your Claude Code context, how much is re-reads and duplicates, and what compaction kept.

  • status
  • pane
  • toast
  • Writes files
  • Intercepts tool calls
  • Reads your prompts
  • Changes the UI
  • Adds commands/tools

tested with v2.1.303

>_ decision-ledger

Decision Ledger

A /decision command that records a choice, the reason and the rejected alternative, tied to a file or symbol.

  • transcript
  • Reads files
  • Runs commands
  • Intercepts tool calls
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.307

>_ dependency-lens

Dependency Lens

Compare package.json and package-lock.json with a Git ref and see direct, transitive and install-script changes.

  • none
  • Reads files
  • Runs commands
  • Intercepts tool calls
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.310

>_ env-doctor

Env Doctor

A /env-doctor command that checks Node and package manager versions against package.json and reports env var presence.

  • none
  • Reads files
  • Runs commands
  • Intercepts tool calls
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.310

>_ handoff-pack

Handoff Pack

A /handoff command that prints a report: goal, tasks, changed files and test results marked PASS, STALE or FAIL.

  • transcript
  • Reads files
  • Runs commands
  • Intercepts tool calls
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.310

Mindful Claude Breathing running in Claude CodeFeatured

Mindful Claude Breathing

Guided breathing animation above the Claude Code prompt while Claude works; the spinner counts the breath with you.

  • above-prompt
  • spinner
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.291

>_ now-playing

Now Playing

The Spotify track, progress bar and synced lyric on a line above the Claude Code prompt, with ⏮ ⏸ ⏭ buttons.

  • above-prompt
  • Reads files
  • Runs commands
  • Network
  • Changes the UI
  • Adds commands/tools

tested with v2.1.310

Pin Memo running in Claude CodeFeatured

Pin Memo

Pin notes and clickable todo checkboxes above the Claude Code prompt with /pin, saved per session.

  • above-prompt
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.303

Recording Mode running in Claude CodeFeatured

Recording Mode

Run /rec before you record: keys, emails, names and money are masked on screen and private files stay closed.

  • above-prompt
  • toast
  • transcript
  • Reads files
  • Writes files
  • Intercepts tool calls
  • Reads your prompts
  • Changes the UI
  • Adds commands/tools

tested with v2.1.310

>_ reels

Reels

YouTube Shorts in a Claude Code pane: plays while Claude works, pauses when Claude is done.

  • pane
  • Reads files
  • Runs commands
  • Network
  • Changes the UI
  • Adds commands/tools

tested with v2.1.310

>_ session-saver

Session Saver

Names untitled sessions through unpause, saves where you left off with /park, and shows that note when you resume.

  • above-prompt
  • toast
  • Reads files
  • Runs commands
  • Calls the model (uses your quota)
  • Reads your prompts
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.307

>_ snake

Snake

Play Snake in a pane while Claude works. It pauses when the turn ends, and nothing opens until you type /snake.

  • pane
  • spinner
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.310

>_ time-machine-midudev

Time Machine

Every turn that changes files becomes a git snapshot; /timeline puts the working tree back as it was before any turn.

  • pane
  • toast
  • Reads files
  • Runs commands
  • Intercepts tool calls
  • Reads your prompts
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.310

Time Machine running in Claude CodeFeatured

Time Machine

A branching timeline of every tool call, with shadow-git snapshots you can diff, restore, branch and rerun.

  • status
  • pane
  • Reads files
  • Writes files
  • Runs commands
  • Intercepts tool calls
  • Reads your prompts
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.303

>_ token-run

Token Run

A small ASCII runner game that offers itself when a Claude Code request fails, or any time with /token-run. Fully local.

  • pane
  • above-prompt
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.310

>_ verify-board

Verify Board

Records your test, lint and typecheck runs and marks each PASS, FAIL, STALE or UNKNOWN against the current git state.

  • none
  • Reads files
  • Runs commands
  • Intercepts tool calls
  • Changes the UI
  • Adds commands/tools
  • Stores data

tested with v2.1.310

Where Am I running in Claude CodeFeatured

Where Am I

A recap above the Claude Code prompt: the session goal, what is happening now, what waits on you and the next step.

  • above-prompt
  • Reads files
  • Calls the model (uses your quota)
  • Intercepts tool calls
  • Reads your prompts
  • Changes the UI
  • Adds commands/tools

tested with v2.1.303

Claude Code slash command mods add commands you type in the prompt, such as /tally or /diff, and answer them in code. Because the handler runs inside Claude Code, it can reply instantly from data the mod has collected, open a pane, or change a setting, with no request to the model and no tokens used.

How do Claude Code slash command mods register a command?

A mod calls $.command.register({ name, description }), usually in its session.start hook, and then handles command.run with a matcher for that name: on('command.run', { command: 'tally' }, ...). The handler returns { text } to print a reply, which renders as Markdown in the transcript, or {} to finish silently. Command names allow letters, digits, _ and -, up to 64 characters.

The same command.run event also fires for every other command, so a mod can wrap built-in commands. command.describe lets a mod change how commands appear in the command list, and $.command.run lets one mod invoke another command. The create guide walks through a /tally example.

What should you check before installing one?

A command mod shows Adds commands/tools. That badge on its own is low risk: the command only runs when you type it. What matters is what the command does when it runs, so read the rest of the badges. A command that reads mod state and prints a table needs nothing else. One that opens a pane adds Changes the UI. One that runs git, reads files or calls a server shows Runs commands, Reads files or Network.

Also check for name clashes. Two mods can try to register the same command name; prefer mods that use a specific name and say so on their page.

When to use a mod command instead of a prompt

Use a mod command when the answer is mechanical: counting, listing, toggling a setting, opening a view. Use a regular command file or a skill when you want Claude to think about the answer. Many useful mods combine both, collecting data in hooks and reporting it through one command.

FAQ

How is a mod command different from a custom command file?
A command file in .claude/commands sends a prompt to Claude. A mod command runs JavaScript in Claude Code and can answer immediately from state the mod collected, without a model request.
Can a mod change a built-in command?
Yes. The command.run hook sees every command before it runs, including built-in ones, and can answer it, change it or pass it on. command.describe changes how a command appears in the list.
Do mod commands work in claude -p?
Yes. Hooks run in print mode, so a command such as claude -p "/tally" works, although nothing is drawn on screen.