AI agent slash commands and key bindings
Type / in the agent to open a filterable list of every command, including
your custom commands and skills. /help prints the same list with key
bindings. Text that starts with / but is not a command, such as a path like
/etc/hosts, is sent to the model as a normal message.
Commands for features your plan does not include are shown greyed out.
Session
Section titled “Session”| Command | Description |
|---|---|
/help | Commands, key bindings, and a link to these docs. |
/new | Start a fresh conversation in this directory. |
/clear | Start a fresh conversation and clear the screen. |
/resume [id] | Reopen any conversation from any surface. |
/continue | Reopen the latest conversation from this directory. |
/rename <title> | Rename the conversation everywhere it appears. |
/rewind | Restore files to their state before an earlier message. |
/export [file.md|file.json] | Export the transcript as Markdown or JSON. |
/copy | Copy the last answer to the clipboard. |
/exit or /quit | Leave the agent. Asks first if background tasks are running. |
Model and context
Section titled “Model and context”| Command | Description |
|---|---|
/model [name] | Show the current model with a menu, or switch. /model auto, /model register, and /model remove <name> are also available. |
/models [name] | Pick a model: Auto, platform models, or models you registered with your own key. |
/effort low|medium|high|max|off | Reasoning effort for models that support it. |
/context | How much of the model’s context the conversation uses, with a breakdown. |
/compact [focus] | Compact the conversation now, optionally saying what to keep. |
/usage or /cost | AI credits used in this session and this billing period. |
See Models.
Work and orchestration
Section titled “Work and orchestration”| Command | Description |
|---|---|
/plan [off] | Enter plan mode: read-only research that ends with a plan you approve. |
/todos | Show the agent’s current task list. |
/agents | List agents and running subagents; run, create, edit, or delete one. |
/tasks | List background subagents, shells, and loops; tail, attach, or stop one. |
/shells or /procs | List running background shells and processes with PIDs, ports, and outputs. |
/loop [--max N] [interval] <prompt> | Run a prompt repeatedly; /loop stop [id] ends it. |
/worktree [name] | Move the session into a new git worktree; /worktree exit returns. |
/review [branch | !<mr>] | Review your pending changes, a branch, or a CHAMPREP Code merge request. |
/security-review [branch] | Security-focused review of the pending changes or a branch. |
/diff | Every file change made in this session. |
/undo | Revert the last set of changes. |
See Subagents, background tasks, and loops.
Connections and extensions
Section titled “Connections and extensions”| Command | Description |
|---|---|
/mcp | MCP servers window: hosted and local servers, status, tools, and actions. See MCP servers. |
/add-dir <path> | Let the agent use another directory for this session. |
/permissions | Show and edit allow and deny rules; mode switches the permission mode. |
/services | Which CHAMPREP services the AI may use. |
/skills [name] | List skills. Run one with /<skill-name>. |
/commands | List custom commands; /commands new <name> creates one. |
/hooks | Show, add, enable, and disable hooks. |
/memory | View or edit CHAMPREP.md files and see your account memory. |
/init | Survey the repository and write a CHAMPREP.md. |
/trust [approve|revoke] | Show or change trust for this repository’s .champrep/ configuration. |
See Customization and Permissions and safety.
Account
Section titled “Account”| Command | Description |
|---|---|
/login | Sign in with the browser. |
/logout | Sign out of this environment. |
/profile | Switch the acting profile: personal, team, or organization. |
/status | Version, profile, environment, model, permission mode, and local paths. |
/doctor | Check installation, sign-in, connectivity, plan, local tools, and terminal. |
/feedback <message> or /bug | Send feedback, optionally with a redacted excerpt. |
/upgrade | Show which version you run and how to update. |
Look and feel
Section titled “Look and feel”| Command | Description |
|---|---|
/logo | Play the animated glowing ChamPrep startup logo in brand blue and cyan. |
/color [name|reset] | Accent colour for this project’s sessions. |
/theme [auto|dark|light|high-contrast|colorblind] | Colour theme. |
/statusline | Choose status line segments or use your own command. Includes shells, agents, and tasks. |
/output-style [default|concise|explanatory|learning] | How answers are written. |
/vim | Toggle vim keys in the prompt editor. |
/keybindings [edit] | View or change key bindings. |
/config | One settings screen for all of the above. |
See Customization.
Key bindings
Section titled “Key bindings”| Key | Action |
|---|---|
Enter | Send the prompt. |
Alt+Enter or Ctrl+J | Insert a newline. Ending a line with \ also works. |
Esc | Interrupt the running turn, including running tools. |
Esc Esc | Open /rewind. |
Shift+Tab | Cycle the permission mode: ask, accept-edits, plan. |
Ctrl+O | Expand or collapse tool output. |
Ctrl+T | Show or hide the task list. |
Ctrl+R | Search prompt history. |
Up / Down | Previous or next prompt. |
Tab | Complete a /command or @path. |
Ctrl+L | Redraw the screen. |
Ctrl+C | Clear the input. Press twice to exit. |
Change bindings with /keybindings edit, which opens
$CONFIG/ai/keybindings.json.
Prompt shortcuts
Section titled “Prompt shortcuts”| Syntax | Effect |
|---|---|
@path | Attach a file from the workspace to the prompt. Tab completes paths. |
@agent-name prompt | Send the prompt to one of your agents as a background subagent. |
!command | Run a shell command yourself in the workspace. Its output (with secrets redacted) is added to your next prompt. |
#text | Save text to the project memory file, CHAMPREP.md. |
!command is run by you, so it does not show a permission prompt. It still
uses a timeout and never receives your CHAMPREP credentials.