Skip to content

Slash Commands

Slash commands are built-in control commands provided by Jarvis Code CLI in the interactive TUI, covering account configuration, session management, mode switching, information queries, and more. Type / in the input box to trigger command completion — the candidate list filters in real time as you continue typing; command aliases are also matched.

After typing the full command name, press Enter to execute. If the /-prefixed input does not match any built-in or Skill command, it is sent to the Agent as a regular message.

TIP

Some commands are only available in the idle state. Executing these commands while a session is streaming output or compacting context will be blocked — press Esc or Ctrl-C to interrupt first. The "Always available" column in the tables below indicates commands that are also available during streaming.

Account & Configuration

CommandAliasDescriptionAlways available
/loginSelect an account or platform and log in: Jarvis Code uses the OAuth device-code flow; the Kimi Open Platform uses API key loginNo
/logout/disconnectClear credentials for the currently selected accountNo
/provider/providersOpen the interactive provider manager to view, add, and remove configured providers. See Platforms & Models — /provider and provider managementYes
/modelSwitch the LLM model used in the current sessionYes
/effort/thinkingSwitch the thinking effort level of the current modelYes
/secondary-model/subagent-modelPick the default model for subagents (writes [secondary_model] default_model; see the subagent model pool). Visible when the subagent model pool experiment is enabledYes
/visual-modelPick the model used to inspect images / videos when the current model is text-only (writes [visual_model] model; see the visual_model section). Only models that declare image, video, or audio input are offeredYes
/settings/configOpen the settings panel inside the TUIYes
/experiments/experimentalOpen the experimental feature panel. Confirmed changes are applied by reloading the current sessionNo
/permissionSelect a permission modeYes
/editorConfigure the external editor launched by Ctrl-GYes
/themeSwitch the terminal UI color themeYes

Session Management

CommandAliasDescriptionAlways available
/new/clearStart a fresh session, discarding the current contextNo
/sessions/resumeBrowse historical sessions and switch to / restore oneNo
/tasks/taskBrowse the background task listYes
/forkFork a new session from the current one, preserving the full conversation history; you stay in the current sessionNo
/title [<text>]/renameWithout arguments, display the current session title; with an argument, set a new title (max 200 characters)Yes
/compact [<instruction>]Compact the current conversation context to free up token usage; an optional custom instruction can hint to the model what to preserveNo
/undo [<count>]Undo recent prompts from the active context. Without a count, opens a selector; with a count, undoes that many prompts. Prompts before the last compaction cannot be undone. Undoing also rolls back the todo list and plan mode state produced by those prompts (code changes are not reverted)No
/reloadReload the current session and apply the latest config.toml settings (providers, models, etc.) and tui.toml UI preferences, without restarting the CLINo
/reload-tuiReload only the tui.toml UI preferences (theme, editor, notifications, etc.) without rebuilding the sessionYes
/initAnalyze the current codebase and generate AGENTS.mdNo
/export-md [<path>]/exportExport the current session as a Markdown fileNo
/export-debug-zipExport the current session as a debug ZIP archive (same behavior as jarvis export)No
/copyCopy the last assistant message to the clipboardNo
/add-dir [<path>]Add an extra workspace directory to the current session. Run without a path (or with list) to list configured directories. When adding, choose whether to remember the directory for the project in .jarvis-code/local.tomlNo

Modes & Run Control

CommandAliasDescriptionAlways available
/yolo [on|off]/yesToggle YOLO mode. Without arguments, flips the current state; explicitly passing on/off forces the setting. When enabled, skips approval for regular tool calls; Plan mode exit approval is not affectedYes
/auto [on|off]Toggle auto permission mode. When enabled, tool approvals are handled automatically and the Agent will not ask the user questionsYes
/plan [on|off]Toggle Plan mode. Without arguments, flips the current state; explicitly passing on/off forces the setting. Simply toggling does not create an empty plan fileYes
/plan clearClear the current planNo
/swarm on|offTurn swarm mode on or off without sending a prompt.No
/swarm <task>Turn swarm mode on, then send <task> as a normal prompt. If the turn completes normally, swarm mode turns off automatically. In manual permission mode, Jarvis Code asks whether to switch to auto or yolo before starting.No
/goal [...]Start or manage an autonomous goalSee below
/tower [...]Report tower status, toggle Tower mode, set the tower objective, or tear the tower down. Requires the tower experiment on the default agent-core-v2 engineYes

WARNING

/yolo skips approval for regular tool calls. Please make sure you understand the potential risks before enabling it. Plan mode exit approval is not bypassed by /yolo; Bash inside Plan mode is still subject to the regular /yolo allow rules.

Autonomous Goal

/goal starts or manages goal mode: a persistent objective that Jarvis Code works toward across automatically continuing turns. For usage guidance and examples, see Goals.

sh
/goal Update the checkout docs, run docs build, and stop if still blocked after 20 turns
CommandActionAvailability
/goal or /goal statusDisplay the current goal along with its status, elapsed time, turn count, and token countAlways available
/goal pausePause an active goal and keep itAlways available
/goal resumeResume a paused or blocked goalIdle only
/goal cancelRemove the current goalAlways available
/goal replace <objective>Replace the saved goal with a new objectiveIdle only
/goal next <objective>Queue an upcoming goal for this session. If no goal is active, start it immediately. The agent does not see queued goals until the current goal completesAlways available
/goal next manageOpen the upcoming-goal manager. Use / to browse, Space to select a goal for moving, selected / to reorder it, E to edit, D to delete, and Esc to cancel. In the edit field, use Shift-Enter or Ctrl-J for a new line and Enter to saveAlways available

The words status, pause, resume, cancel, replace, and next act as subcommands only when they are the first word after /goal. If your objective needs to start with one of those words, put -- before it:

sh
/goal -- cancel the old rollout note after the new docs are published

If an upcoming goal needs to start with manage, put -- after next:

sh
/goal next -- manage the release checklist

In non-interactive prompt mode, only the create forms start goal mode:

sh
jarvis -p "/goal Fix the failing checkout test"

Prompt mode exits with code 0 when the goal completes, 3 when it blocks, and 6 when it pauses. Other /goal subcommands, including next, are TUI controls and are not handled by jarvis -p.

Tower mode

/tower drives Tower mode: an experimental mode in which the main agent stops writing code and instead coordinates worker and reviewer subagents, each in its own git worktree, merging only review-approved branches.

The command is only visible when the tower experimental flag is enabled (JARVIS_CODE_EXPERIMENTAL_TOWER=1, or the master switch JARVIS_CODE_EXPERIMENTAL_FLAG=1) on the default agent-core-v2 engine. Enabling the flag from /experiments requires a restart before the mode works, because the tower tools are assembled once at startup.

sh
/tower Split the renderer refactor across the build, shader, and test layers and land it on main
CommandAction
/tower or /tower statusAsk the tower to report the current dashboard
/tower onTurn Tower mode on without sending an objective
/tower offTurn Tower mode off
/tower teardownAsk the tower to tear the workspace down and report the final summary
/tower <objective>Turn Tower mode on and send <objective> as the next prompt

Every form stays available while the agent is busy: an objective sent mid-turn steers into the running coordinator turn instead of waiting. Turning the mode on fails with an explanation when the experiment is off, when it was just enabled and needs a restart, or when another session already owns this workspace's tower.

Dynamic Workflows

/workflow (alias /workflows) manages dynamic workflows — JavaScript scripts that orchestrate subagents. Runs proposed by the model require your approval in manual permission mode; in yolo and auto modes they are approved automatically.

CommandDescription
/workflow listList all discovered workflows
/workflow run <name> [args]Run a workflow by name, passing args to the script
/workflow runsOpen the run browser: status, current phase, agent calls, logs, and result/error of each run
/workflow show <name>Show a workflow's metadata and script
/workflow cancel <runId>Cancel a running workflow
/workflow save <runId> [--user]Save the script of a run into the project workflow directory (.jarvis-code/workflows/); with --user, into the user directory (~/.jarvis-code/workflows/)
/workflow reloadRescan the workflow directories
/workflow onEnable Dynamic Workflow mode manually: the model analyses the task first and proposes dynamic workflows for large multi-phase tasks (with the flag on, the mode also engages automatically)
/workflow offDisable Dynamic Workflow mode

Information & Status

CommandAliasDescriptionAlways available
/help/h, /?Show keyboard shortcuts and all available commandsYes
/btw [question]Open a side conversation in a forked sub-Agent without affecting the current main Agent turn; without a question, opens the panel first to wait for inputYes
/usageShow token usage, context consumption, and quota informationYes
/statusShow the current session runtime state: version, model, working directory, permission mode, etc.Yes
/memoryOn engine v2, manage persistent memories: list, create (N), edit (E), view (Enter), and forget (D). Create and edit open the memory as a markdown document in $EDITORYes
/mcpList MCP servers and their connection status in the current sessionYes
/pluginsOpen the interactive plugin managerYes
/versionDisplay the Jarvis Code CLI version numberYes
/feedback/bugSubmit feedback with optional diagnostic logs and codebase contextYes

Exit

CommandAliasDescriptionAlways available
/exit/quit, /qExit Jarvis Code CLINo

Built-in skill commands

Jarvis Code CLI ships with a set of built-in Skills that appear directly as /<name> slash commands. Unlike external Skills, they do not require the skill: prefix and are available out of the box.

CommandDescription
/mcp-configConfigure MCP servers and handle MCP OAuth login. See MCP
/custom-theme [<text>]Create or edit a custom TUI color theme. See Themes
/update-configInspect or edit config.toml (model, provider, permission, hooks) and tui.toml (theme, editor, notifications, auto-update)
/check-jarvis-code-docsAnswer Jarvis Code product questions (CLI usage, configuration, tools, error messages) against the official docs
/write-goalTurn a rough intention into a well-specified /goal objective with a finish line, proof, boundaries, and a stop rule. See Using goals
/import-from-cc-codexImport Claude Code and Codex instructions, skills, and MCP settings into Jarvis Code
/sub-skillDiscover and reorganize the local skill inventory into hierarchical sub-skill bundles. Includes /sub-skill.review (read-only proposal) and /sub-skill.consolidate (apply the reorganization)

All built-in Skill commands are only available in the idle state.

Skill Dynamic Commands

Activated external Skills are automatically registered as slash commands. Ordinary external Skills use the skill: namespace prefix:

/skill:<name> [extra text]

For example, /skill:code-style loads the Skill named code-style and sends it to the Agent; any text appended after the command is concatenated to the Skill prompt.

External sub-skills appear directly in the slash command panel with dotted names:

/<parent-skill>.<sub-skill> [extra text]

For example, a child Skill named review inside a parent Skill named code-style is shown as /code-style.review. The dotted command name is derived from the hierarchy; the child SKILL.md can keep its local name.

For convenience, external Skill commands also support a shorthand form that omits the skill: prefix — /<name> — as long as the name is not taken by a system slash command. That is, /code-style falls back to matching /skill:code-style.

Built-in Skills shipped with Jarvis Code CLI appear directly as /<name> in the slash command panel. For example, /mcp-config helps configure MCP servers and handle MCP OAuth login, and /custom-theme [extra text] invokes the custom-theme workflow to create or edit a TUI theme.

INFO

External Skill commands entered while the agent is busy are queued behind the running turn instead of being rejected — press Ctrl-S to steer a queued command into the running turn immediately. flow-type Skills are also exposed via /skill:<name> — there is no separate /flow: namespace.

For installing and authoring Skills, see Agent Skills.

Next steps