1|---
 2|lang: ru
 3|sidebar_position: 2
 4|title: "Slash Commands Reference"
 5|description: "Complete reference for interactive CLI and messaging slash commands"
 6|---
 7|
 8|# Slash Commands Reference
 9|
10|Hermes has two slash-command surfaces, both driven by a central `COMMAND_REGISTRY` in `hermes_cli/commands.py`:
11|
12|- **Interactive CLI slash commands**  dispatched by `cli.py`, with autocomplete from the registry
13|- **Messaging slash commands**  dispatched by `gateway/run.py`, with help text and platform menus generated from the registry
14|
15|Installed skills are also exposed as dynamic slash commands on both surfaces. That includes bundled skills like `/plan`, which opens plan mode and saves markdown plans under `.hermes/plans/` relative to the active workspace/backend working directory.
16|
17|## Interactive CLI slash commands
18|
19|Type `/` in the CLI to open the autocomplete menu. Built-in commands are case-insensitive.
20|
21|### Session
22|
23|| Command | Description |
24||---------|-------------|
25|| `/new` (alias: `/reset`) | Start a new session (fresh session ID + history) |
26|| `/clear` | Clear screen and start a new session |
27|| `/history` | Show conversation history |
28|| `/save` | Save the current conversation |
29|| `/retry` | Retry the last message (resend to agent) |
30|| `/undo` | Remove the last user/assistant exchange |
31|| `/title` | Set a title for the current session (usage: /title My Session Name) |
32|| `/compress [focus topic]` | Manually compress conversation context (flush memories + summarize). Optional focus topic narrows what the summary preserves. |
33|| `/rollback` | List or restore filesystem checkpoints (usage: /rollback [number]) |
34|| `/snapshot [create\|restore <id>\|prune]` (alias: `/snap`) | Create or restore state snapshots of Hermes config/state. `create [label]` saves a snapshot, `restore <id>` reverts to it, `prune [N]` removes old snapshots, or list all with no args. |
35|| `/stop` | Kill all running background processes |
36|| `/queue <prompt>` (alias: `/q`) | Queue a prompt for the next turn (doesn't interrupt the current agent response). |
37|| `/steer <prompt>` | Inject a mid-run note that arrives at the agent **after the next tool call**  no interrupt, no new user turn. The text is appended to the last tool result's content once the current tool completes, giving the agent new context without breaking the current tool-calling loop. Use this to nudge direction mid-task (e.g. "focus on the auth module" while the agent is running tests). |
38|| `/goal <text>` | Set a standing goal Hermes works toward across turns  our take on the Ralph loop. After each turn an auxiliary judge model decides whether the goal is done; if not, Hermes auto-continues. Subcommands: `/goal status`, `/goal pause`, `/goal resume`, `/goal clear`. Budget defaults to 20 turns (`goals.max_turns`); any real user message preempts the continuation loop, and state survives `/resume`. See [Persistent Goals](/docs/user-guide/features/goals) for the full walkthrough. |
39|| `/resume [name]` | Resume a previously-named session |
40|| `/redraw` | Force a full UI repaint (recovers from terminal drift after tmux resize, mouse selection artifacts, etc.) |
41|| `/status` | Show session info |
42|| `/agents` (alias: `/tasks`) | Show active agents and running tasks across the current session. |
43|| `/background <prompt>` (alias: `/bg`, `/btw`) | Run a prompt in a separate background session. The agent processes your prompt independently  your current session stays free for other work. Results appear as a panel when the task finishes. See [CLI Background Sessions](/docs/user-guide/cli#background-sessions). |
44|| `/branch [name]` (alias: `/fork`) | Branch the current session (explore a different path) |
45|
46|### Configuration
47|
48|| Command | Description |
49||---------|-------------|
50|| `/config` | Show current configuration |
51|| `/model [model-name]` | Show or change the current model. Supports: `/model claude-sonnet-4`, `/model provider:model` (switch providers), `/model custom:model` (custom endpoint), `/model custom:name:model` (named custom provider), `/model custom` (auto-detect from endpoint). Use `--global` to persist the change to config.yaml. **Note:** `/model` can only switch between already-configured providers. To add a new provider, exit the session and run `hermes model` from your terminal. |
52|| `/personality` | Set a predefined personality |
53|| `/verbose` | Cycle tool progress display: off  new  all  verbose. Can be [enabled for messaging](#notes) via config. |
54|| `/fast [normal\|fast\|status]` | Toggle fast mode  OpenAI Priority Processing / Anthropic Fast Mode. Options: `normal`, `fast`, `status`. |
55|| `/reasoning` | Manage reasoning effort and display (usage: /reasoning [level\|show\|hide]) |
56|| `/skin` | Show or change the display skin/theme |
57|| `/statusbar` (alias: `/sb`) | Toggle the context/model status bar on or off |
58|| `/voice [on\|off\|tts\|status]` | Toggle CLI voice mode and spoken playback. Recording uses `voice.record_key` (default: `Ctrl+B`). |
59|| `/yolo` | Toggle YOLO mode  skip all dangerous command approval prompts. |
60|| `/footer [on\|off\|status]` | Toggle the gateway runtime-metadata footer on final replies (shows model, tool counts, timing). |
61|| `/busy [queue\|steer\|interrupt\|status]` | CLI-only: control what pressing Enter does while Hermes is working  queue the new message, steer mid-turn, or interrupt immediately. |
62|| `/indicator [kaomoji\|emoji\|unicode\|ascii]` | CLI-only: pick the TUI busy-indicator style. |
63|
64|### Tools & Skills
65|
66|| Command | Description |
67||---------|-------------|
68|| `/tools [list\|disable\|enable] [name...]` | Manage tools: list available tools, or disable/enable specific tools for the current session. Disabling a tool removes it from the agent's toolset and triggers a session reset. |
69|| `/toolsets` | List available toolsets |
70|| `/browser [connect\|disconnect\|status]` | Manage local Chrome CDP connection. `connect` attaches browser tools to a running Chrome instance (default: `ws://localhost:9222`). `disconnect` detaches. `status` shows current connection. Auto-launches Chrome if no debugger is detected. |
71|| `/skills` | Search, install, inspect, or manage skills from online registries |
72|| `/cron` | Manage scheduled tasks (list, add/create, edit, pause, resume, run, remove) |
73|| `/curator` | Background skill maintenance  `status`, `run`, `pin`, `archive`. See [Curator](/docs/user-guide/features/curator). |
74|| `/kanban <action>` | Drive the multi-profile, multi-project collaboration board without leaving chat. Full `hermes kanban` surface is available: `/kanban list`, `/kanban show t_abc`, `/kanban create "title" --assignee X`, `/kanban comment t_abc "text"`, `/kanban unblock t_abc`, `/kanban dispatch`, etc. Multi-board support included: `/kanban boards list`, `/kanban boards create <slug>`, `/kanban boards switch <slug>`, `/kanban --board <slug> <action>`. See [Kanban slash command](/docs/user-guide/features/kanban#kanban-slash-command). |
75|| `/reload-mcp` (alias: `/reload_mcp`) | Reload MCP servers from config.yaml |
76|| `/reload` | Reload `.env` variables into the running session (picks up new API keys without restarting) |
77|| `/plugins` | List installed plugins and their status |
78|
79|### Info
80|
81|| Command | Description |
82||---------|-------------|
83|| `/help` | Show this help message |
84|| `/usage` | Show token usage, cost breakdown, session duration, and  when available from the active provider  an **Account limits** section with remaining quota / credits / plan usage pulled live from the provider's API. |
85|| `/insights` | Show usage insights and analytics (last 30 days) |
86|| `/platforms` (alias: `/gateway`) | Show gateway/messaging platform status |
87|| `/paste` | Attach a clipboard image |
88|| `/copy [number]` | Copy the last assistant response to clipboard (or the Nth-from-last with a number). CLI-only. |
89|| `/image <path>` | Attach a local image file for your next prompt. |
90|| `/debug` | Upload debug report (system info + logs) and get shareable links. Also available in messaging. |
91|| `/profile` | Show active profile name and home directory |
92|| `/gquota` | Show Google Gemini Code Assist quota usage with progress bars (only available when the `google-gemini-cli` provider is active). |
93|
94|### Exit
95|
96|| Command | Description |
97||---------|-------------|
98|| `/quit` | Exit the CLI (also: `/exit`). |
99|

100|### Dynamic CLI slash commands 101| 102|| Command | Description | 103||---------|-------------| 104|| /<skill-name> | Load any installed skill as an on-demand command. Example: /gif-search, /github-pr-workflow, /excalidraw. | 105|| /skills... | Search, browse, inspect, install, audit, publish, and configure skills from registries and the official optional-skills catalog. | 106| 107|### Quick Commands 108| 109|User-defined quick commands map a short slash command to either a shell command or another slash command. Configure them in ~/.hermes/config.yaml: 110| 111|yaml 112|quick_commands: 113| status: 114| type: exec 115| command: systemctl status hermes-agent 116| deploy: 117| type: exec 118| command: scripts/deploy.sh 119| inbox: 120| type: alias 121| target: /gmail unread 122| 123| 124|Then type /status, /deploy, or /inbox in the CLI or a messaging platform. Quick commands are resolved at dispatch time and may not appear in every built-in autocomplete/help table. 125| 126|String-only prompt shortcuts are not supported as quick commands. Put longer reusable prompts in a skill, or use type: alias to point at an existing slash command. 127| 128|### Alias Resolution 129| 130|Commands support prefix matching: typing /h resolves to /help, /mod resolves to /model. When a prefix is ambiguous (matches multiple commands), the first match in registry order wins. Full command names and registered aliases always take priority over prefix matches. 131| 132|## Messaging slash commands 133| 134|The messaging gateway supports the following built-in commands inside Telegram, Discord, Slack, WhatsApp, Signal, Email, Home Assistant, and Teams chats: 135| 136|| Command | Description | 137||---------|-------------| 138|| /new | Start a new conversation. | 139|| /reset | Reset conversation history. | 140|| /status | Show session info. | 141|| /stop | Kill all running background processes and interrupt the running agent. | 142|| /model [provider:model] | Show or change the model. Supports provider switches (/model zai:glm-5), custom endpoints (/model custom:model), named custom providers (/model custom:local:qwen), and auto-detect (/model custom). Use --global to persist the change to config.yaml. Note: /model can only switch between already-configured providers. To add a new provider or set up API keys, use hermes model from your terminal (outside the chat session). | 143|| /personality [name] | Set a personality overlay for the session. | 144|| /fast [normal\|fast\|status] | Toggle fast mode — OpenAI Priority Processing / Anthropic Fast Mode. | 145|| /retry | Retry the last message. | 146|| /undo | Remove the last exchange. | 147|| /sethome (alias: /set-home) | Mark the current chat as the platform home channel for deliveries. | 148|| /compress [focus topic] | Manually compress conversation context. Optional focus topic narrows what the summary preserves. | | /topic [off|help|session-id] | Только Telegram DM. Управление многосессионным режимом тем. /topic включает его или показывает статус; /topic off отключает и очищает привязки; /topic help показывает справку; /topic <session-id> внутри темы восстанавливает предыдущую сессию. См. Многосессионный режим DM. | 150|| /title [name] | Set or show the session title. | 151|| /resume [name] | Resume a previously named session. | 152|| /usage | Show token usage, estimated cost breakdown (input/output), context window state, session duration, and — when available from the active provider — an Account limits section with remaining quota / credits pulled live from the provider's API. | 153|| /insights [days] | Show usage analytics. | 154|| /reasoning [level\|show\|hide] | Change reasoning effort or toggle reasoning display. | 155|| /voice [on\|off\|tts\|join\|channel\|leave\|status] | Control spoken replies in chat. join/channel/leave manage Discord voice-channel mode. | 156|| /rollback [number] | List or restore filesystem checkpoints. | 157|| /background <prompt> | Run a prompt in a separate background session. Results are delivered back to the same chat when the task finishes. See Messaging Background Sessions. | 158|| /queue <prompt> (alias: /q) | Queue a prompt for the next turn without interrupting the current one. | 159|| /steer <prompt> | Inject a message after the next tool call without interrupting — the model picks it up on its next iteration rather than as a new turn. | 160|| /goal <text> | Set a standing goal Hermes works toward across turns — our take on the Ralph loop. A judge model checks after each turn; if not done, Hermes auto-continues until it is, you pause/clear it, or the turn budget (default 20) is hit. Subcommands: /goal status, /goal pause, /goal resume, /goal clear. Safe to run mid-agent for status/pause/clear; setting a new goal requires /stop first. See Persistent Goals. | 161|| /footer [on\|off\|status] | Toggle the runtime-metadata footer on final replies (shows model, tool counts, timing). | 162|| /curator [status\|run\|pin\|archive] | Background skill maintenance controls. | 163|| /kanban <action> | Drive the multi-profile, multi-project collaboration board from chat — identical argument surface to the CLI. Bypasses the running-agent guard, so /kanban unblock t_abc, /kanban comment t_abc "…", /kanban list --mine, /kanban boards switch <slug>, etc. work mid-turn. /kanban create … auto-subscribes the originating chat to the new task's terminal events. See Kanban slash command. | 164|| /reload-mcp (alias: /reload_mcp) | Reload MCP servers from config. | 165|| /yolo | Toggle YOLO mode — skip all dangerous command approval prompts. | 166|| /commands [page] | Browse all commands and skills (paginated). | 167|| /approve [session\|always] | Approve and execute a pending dangerous command. session approves for this session only; always adds to permanent allowlist. | 168|| /deny | Reject a pending dangerous command. | 169|| /update | Update Hermes Agent to the latest version. | 170|| /restart | Gracefully restart the gateway after draining active runs. When the gateway comes back online, it sends a confirmation to the requester's chat/thread. | 171|| /debug | Upload debug report (system info + logs) and get shareable links. | 172|| /help | Show messaging help. | 173|| /<skill-name> | Invoke any installed skill by name. | 174| 175|## Notes 176| 177|- /skin, /snapshot, /gquota, /reload, /tools, /toolsets, /browser, /config, /cron, /skills, /platforms, /paste, /image, /statusbar, /plugins, /busy, /indicator, /redraw, /clear, /history, /save, /copy, and /quit are CLI-only commands. 178|- /verbose is CLI-only by default, but can be enabled for messaging platforms by setting display.tool_progress_command: true in config.yaml. When enabled, it cycles the display.tool_progress mode and saves to config. 179|- /sethome, /update, /restart, /approve, /deny, /topic и /commandsтолько для обмена сообщениями. 180|- /status, /background, /queue, /steer, /voice, /reload-mcp, /rollback, /debug, /fast, /footer, /curator, /kanban, and /yolo work in both the CLI and the messaging gateway. 181|- /voice join, /voice channel, and /voice leave are only meaningful on Discord. 182|