Nous Hermes Commands & Prompt Reference
105 commands & parameters · 7 categories · Source: Hermes 4 model card & Hermes Agent docs
Nous Research's Hermes spans two typed surfaces: the prompt format of the open Hermes 4 models, and the slash commands of Hermes Agent, the terminal-native agent built on them. The model side is small but precise - Hermes 4 405B speaks the Llama 3.1 header-token format, reasoning mode is switched with the thinking=True chat-template flag or the official deep-thinking system prompt, internal reasoning arrives inside <think> tags, and tool calling uses the <tools>, <tool_call>, and <tool_response> tag protocol documented on the model card.
Hermes Agent's command set reads like a superset of most coding agents: session branching with /branch, git worktrees with /worktree, background runs with /background, plus operational commands for gateways, billing, and approvals. Everything here is taken from the official slash-command reference; commands marked CLI-only do not work from messaging channels.
One practical note on the model side: the reasoning system prompt is not all-or-nothing. The model card states you can add instructions before or after it to adjust thinking effort, style, and output format, and interleave it with the tool-definition system message.
All Commands
Hermes 4 Prompt Format & Tool Calling (8)
| Command / Syntax | What it does | Notes |
|---|---|---|
| <|start_header_id|>role<|end_header_id|> | Llama 3.1 chat header tokens used by Hermes 4 405B | Roles: system, user, assistant. Each turn ends with <|eot_id|>. Smaller Hermes 4 models use ChatML instead. |
| <|eot_id|> | End-of-turn token in the 405B prompt format | Closes each header-delimited message. |
| thinking=True | Chat template flag that activates reasoning mode | Pass to the tokenizer chat template; alternatively use the deep-thinking system prompt from the model card. |
| <think> </think> | Tags enclosing the model's internal reasoning | Emitted when reasoning mode is active; strip them to get the final answer only. |
| You are a deep thinking AI... | Official reasoning-mode system prompt | Full text on the model card. Additional system instructions before or after it adjust thinking effort, style, and format. |
| <tools> </tools> | System-prompt tags wrapping the JSON tool signatures | Function definitions go inside these tags in the system message. |
| <tool_call> </tool_call> | Tags the model emits around a JSON function call | Parse the JSON inside to execute the call. |
| <tool_response> </tool_response> | Tags wrapping the tool result you feed back | Return the function output inside these tags in a tool role message. |
Session (CLI) (32)
| Command / Syntax | What it does | Notes |
|---|---|---|
| /new [name] (alias: /reset ) | Start a new session (fresh session ID + history). | Optional [name] sets the initial session title — e.g. /new my-experiment opens a fresh session already titled my-experiment so it's easy to find later with /resume or /sessions . Append now , --yes , or -y to skip the confirmation modal — e.g. /reset now , /new --yes my-experimen |
| /clear | Clear screen and start a new session | |
| /history | Show conversation history (respects /timestamps ) | |
| /save | Save the current conversation | |
| /prompt (alias: /compose ) | Compose your next prompt in $EDITOR (markdown) instead of the inline input — useful for long, multi-line, or carefully-formatted prompts. | |
| /retry | Retry the last message (resend to agent) | |
| /undo | Remove the last user/assistant exchange | |
| /title | Set a title for the current session (usage: /title My Session Name) | |
| /compress [here [N] | focus topic] | Manually compress conversation context (flush memories + summarize). | /compress here [N] summarizes everything except the most recent N exchanges (default 2), kept verbatim — pick your own compression boundary. A focus topic narrows what a full summary preserves. |
| /rollback | List or restore filesystem checkpoints (usage: /rollback [number]) | |
| /diff [staged|all|session] [--stat] [path...] | Show git changes in the working directory. | Default: unstaged changes plus untracked files. staged shows what's staged for commit, all everything since HEAD, and session the cumulative diff of everything Hermes changed here (from the earliest retained checkpoint baseline — requires checkpoints to be enabled; complements /r |
| /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. |
| /stop | Kill all running background processes | |
| /queue <prompt> (alias: /q ) | Queue a prompt for the next turn (doesn't interrupt the current agent response). | |
| /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). |
| /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, |
| /subgoal <text> | Append a user-supplied criterion to the active goal mid-loop. | The continuation prompt surfaces all subgoals to the agent verbatim, and the judge factors them into its DONE/CONTINUE verdict — so the goal isn't marked done until the original goal and every subgoal are met. Subcommands: /subgoal (list), /subgoal remove <N> , /subgoal clear . R |
| /heartbeat every <interval> <prompt> (alias: /hb ) | Set a recurring prompt that re-enters this session as a normal user turn whenever it's idle and the interval has elapsed (min 60s; missed ticks coalesce). | Subcommands: /heartbeat status , /heartbeat pause , /heartbeat resume , /heartbeat clear . Session-scoped and in-process — use hermes cron for durable isolated schedules. See Session Heartbeats . |
| /refine [focus] | Run the background memory/skill self-improvement review now instead of waiting for the automatic post-turn trigger. | Optional focus text steers the review (e.g. /refine save the deploy workflow as a skill ). Runs in a background fork against a conversation snapshot — the live session and prompt cache are untouched; results are reported when done. |
| /moa <prompt> | Run a single prompt through the default Mixture of Agents preset, then restore your current model. | One-shot — does not change your session model. |
| /resume [name] | Resume a previously-named session | |
| /sessions (TUI alias: /switch ) | Classic CLI: browse and resume previous sessions in an interactive picker. | TUI: open the live session switcher for currently open TUI sessions. Use /sessions new in the TUI to start another live session immediately. |
| /egress [status] | Show Docker egress proxy status — enabled/configured/running state, credential source, token mappings, uncovered providers, and next remediation step. | Works in CLI, TUI, Desktop chat, and messaging gateway. |
| /redraw | Force a full UI repaint (recovers from terminal drift after tmux resize, mouse selection artifacts, etc.) | |
| /status | Show session info — model, provider, profile, session ID, working directory, title, created/updated timestamps, token totals, agent-running state — followed by a local Session reca | The recap is computed locally from the in-memory conversation; no LLM call, no prompt-cache impact. |
| /context [all] (alias: /ctx ) | Visual context-window breakdown. | On the CLI/TUI: a 5×20 glyph block grid (each cell ≈ 1% of the model window) plus an estimated per-category table — system prompt, tool definitions, rules, skills index, MCP, subagents, memory, conversation — versus free space. On messaging platforms: a usage gauge with auto-comp |
| /agents (alias: /tasks ) | Show active agents and running tasks across the current session. | |
| /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 . |
| /branch [name] (alias: /fork ) | Branch the current session (explore a different path) | |
| /worktree [new [name]|list] | CLI only. | Inspect or create isolated git worktrees mid-session (inspired by Copilot CLI's /worktree new ). Bare /worktree shows the active worktree; /worktree list lists the repo's worktrees; /worktree new [name] creates a worktree under .worktrees/ (branched from the freshly-fetched remot |
| /handoff <platform> | CLI only. | Hand the current session off to a messaging platform (Telegram, Discord, Slack, WhatsApp, Signal, Matrix). The gateway picks it up immediately, creates a fresh thread on platforms that support threads (Telegram topics, Discord text-channel threads, Slack message-anchored threads) |
| /journey [list|delete <id>|edit <id>] (aliases: /learning , /memory-graph ) | Open the learning journey timeline of learned skills + memories. | Works in the classic CLI, as a TUI overlay, and in the desktop app (Star Map panel). Not available on messaging platforms. See Learning Journey . |
Configuration (CLI) (21)
| Command / Syntax | What it does | Notes |
|---|---|---|
| /config | Show current configuration | |
| /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), and user-defined aliases ( /model fav , /model grok — see Custom model |
| /codex-runtime [auto|codex_app_server|on|off] | Toggle the optional Codex app-server runtime for OpenAI/Codex models. | auto (default) uses Hermes' standard chat completions; codex_app_server hands turns to a codex app-server subprocess for native shell, apply_patch, ChatGPT subscription auth, and migrated Codex plugins. Effective on next session. |
| /personality | Set a predefined personality. | /personality none (or default / neutral ) clears the overlay and returns to base behavior. |
| /verbose | Cycle tool progress display: off → new → all → verbose. | Can be enabled for messaging via config. |
| /focus [on|off|status] | Toggle focus view — a display-only reduced-output mode showing just your prompt and the final response. | Composes with /verbose : turning it on snaps tool progress to off and remembers your previous mode, and /focus off restores it. Each turn ends with a dim recovery line ( ⋯ 7 tool lines hidden · /focus off to show ) and a persistent ◉ focus badge sits in the status bar so you alwa |
| /fast [normal|fast|status] | Toggle fast mode — OpenAI Priority Processing / Anthropic Fast Mode. | Options: normal , fast , status . |
| /reasoning [level|show|hide|full|clamp] [--global] | Manage reasoning effort and display. | Levels include none / minimal / low / medium / high / xhigh / max / ultra . show / hide (or on / off ) toggle reasoning display; full and clamp adjust how reasoning is shown. --global persists effort to config. |
| /skin | Show or change the display skin/theme | |
| /export [profile] [-o out.tar.gz] | CLI only. | Pack a profile into a shareable .tar.gz — skills, memory, persona, crons, plugins, settings, and (from the desktop) themes and layout. Credentials ( auth.json , .env ) are stripped. Defaults to the active profile and <name>.tar.gz in the current directory. Same archive as hermes |
| /import <archive.tar.gz> [--name <name>] | CLI only. | Install a profile archive as a new profile, inferring the name from the archive unless --name is given. Refuses to overwrite an existing profile and cannot import as default . Creates a shell wrapper when the name is free. See Export and import a profile file . |
| /statusbar (alias: /sb ) | Toggle the context/model status bar on or off | |
| /battery [on|off|status] | Toggle a color-coded battery read-out as the first status-bar element (off by default; no-op without a battery). | |
| /voice [on|off|tts|status] | Toggle CLI voice mode and spoken playback. | Recording uses voice.record_key (default: Ctrl+B ). |
| /yolo | Toggle YOLO mode — skip all dangerous command approval prompts. | |
| /approvals [manual|smart|off] | Show or set the persistent dangerous-command approval mode. | |
| /footer [on|off|status] | Toggle the gateway runtime-metadata footer on final replies (shows model, context %, and cwd). | |
| /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. | |
| /indicator [kaomoji|emoji|unicode|ascii] | CLI-only: pick the TUI busy-indicator style. | |
| /timestamps [on|off|status] | CLI-only: toggle [HH:MM] timestamps on messages and in /history . | |
| /wake [on|off|status] | CLI-only: toggle the "Hey Hermes" wake word listener. |
Tools & Skills (CLI) (19)
| Command / Syntax | What it does | Notes |
|---|---|---|
| /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. |
| /toolsets | List available toolsets | |
| /browser [connect|disconnect|status] | Manage a local Chromium-family CDP connection. | connect attaches browser tools to a running Chrome, Brave, Chromium, or Edge instance (default: http://127.0.0.1:9222 ). disconnect detaches. status shows current connection. Auto-launches a supported Chromium-family browser if no debugger is detected. |
| /skills | Search, install, inspect, or manage skills from online registries. | Also the review surface for the skill write-approval gate: /skills pending , /skills diff <id> , /skills approve <id> , /skills reject <id> , /skills approval on|off . See Gating agent skill writes . |
| /memory [pending|approve|reject|approval] | Review pending memory writes staged by the write-approval gate ( memory.write_approval ) and toggle the gate. | See Controlling memory writes . |
| /bundles | List configured skill bundles — /<name> slash aliases that preload several skills at once. | Configure under bundles: in ~/.hermes/config.yaml . See Skill Bundles . |
| /learn <what to learn from> | Distill a reusable skill from anything you describe — a directory, a URL, the workflow you just walked the agent through, or pasted notes. | Open-ended: the agent gathers the sources with its own tools and authors a SKILL.md following the house authoring standards. Works in the CLI, the messaging gateway, the TUI, and the dashboard Skills page. |
| /init [notes] | Generate or update AGENTS.md project instructions from a repo scan (port of Codex /init ). | The agent inspects manifests, layout, and toolchain configs with its read-only tools, then writes a concise AGENTS.md — or, if one exists, merge-updates it preserving your content. Optional notes steer the emphasis. Works in the CLI, the messaging gateway, and the TUI. |
| /cron | Manage scheduled tasks (list, add/create, edit, pause, resume, run, remove) | |
| /suggestions [accept|dismiss N|catalog|clear] (alias: /suggest ) | Review suggested automations. | Use /suggestions to list pending suggestions, /suggestions accept <id> to create the proposed automation, /suggestions dismiss <id> to reject one, /suggestions catalog to add curated starter automations, and /suggestions clear to clear resolved suggestion records. Accepted jobs p |
| /blueprint [name] [slot=value ...] (alias: /bp ) | Set up an automation from a blueprint template. | Bare /blueprint lists the catalog; /blueprint <name> starts a guided slot-filling flow on the next agent turn; /blueprint <name> slot=value ... creates the job directly. |
| /curator | Background skill maintenance — status , run , pin , archive . | See Curator . |
| /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> , /ka |
| /reload-mcp (alias: /reload_mcp ) | Reload MCP servers from config.yaml | |
| /reload-skills (alias: /reload_skills ) | Re-scan ~/.hermes/skills/ for newly installed or removed skills | |
| /reload | Reload .env variables into the running session (picks up new API keys without restarting) | |
| /plugins | List installed plugins and their status | |
| /pet [list|<slug>] | Toggle or adopt a petdex mascot. | /pet toggles the pane, /pet list shows installed pets, /pet <slug> adopts a specific one. |
| /hatch <description> (alias: /generate-pet ) | Generate a brand-new petdex pet from a text description, using the configured image backend (OpenRouter / Nous Portal). | See Pets . |
Info & Account (CLI) (15)
| Command / Syntax | What it does | Notes |
|---|---|---|
| /help | Show available commands, grouped by category. | Core commands are shown by default with skill commands collapsed to a one-line count; /help skills lists all skill commands, and /help <text> filters commands (and matching skills) by substring. |
| /palette | Open the fuzzy command palette (also Ctrl+P ) — type to filter all commands + skills, ↑/↓ to move, Enter to insert the selected command into the composer (never auto-runs), Esc to | Matching is ranked by command name first, so a short query stays precise. |
| /version | Show Hermes Agent version, build, and environment info. | |
| /whoami | Show your slash command access level (admin / user). | |
| /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 liv | |
| /topup | Show your Nous balance and manage billing on the portal (replaces the old /credits and /billing commands). | |
| /subscription (alias: /upgrade ) | CLI only. | View your Nous plan and change it in the browser. |
| /insights | Show usage insights and analytics (last 30 days) | |
| /update | Update Hermes Agent to the latest version. | |
| /platforms (alias: /gateway ) | Show gateway/messaging platform status (CLI-only summary view). | |
| /paste | Attach a clipboard image | |
| /copy [number] | Copy the last assistant response to clipboard (or the Nth-from-last with a number). | CLI-only. |
| /image <path> | Attach a local image file for your next prompt. | |
| /debug | Upload debug report (system info + logs) and get shareable links. | Also available in messaging. |
| /profile | Show active profile name and home directory |
Exit (CLI) (1)
| Command / Syntax | What it does | Notes |
|---|---|---|
| /quit | Exit the CLI (also: /exit ). |
Messaging-Only Commands (9)
| Command / Syntax | What it does | Notes |
|---|---|---|
| /start | Platform-protocol command. | Many chat platforms (Telegram, Discord, …) send /start automatically the first time a user opens a bot conversation. Hermes acknowledges the ping silently — no agent reply, no session burn — so first-contact handshakes don't waste a turn. You can also send it explicitly to confir |
| /sethome (alias: /set-home ) | Mark the current chat as the platform home channel for deliveries. | |
| /topic [off|help|session-id] | Telegram DM only. | Manage user-managed multi-session topic mode. /topic enables it or shows status; /topic off disables it and clears bindings; /topic help shows usage; /topic <session-id> inside a topic restores a previous session. See Multi-session DM mode . |
| /platform <list|pause|resume> [name] | Operate a running gateway platform right from chat. | /platform list shows every adapter and its state (running, paused-by-breaker, manually-paused); /platform pause <name> stops dispatching new messages to that adapter without unloading it; /platform resume <name> re-enables it and clears a tripped circuit breaker once the upstream |
| /commands [page] | Browse all commands and skills (paginated). | |
| /approve [session|always] | Approve and execute a pending dangerous command. | session approves for this session only; always adds to permanent allowlist. |
| /deny | Reject a pending dangerous command. | |
| /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. |
| /<skill-name> | Invoke any installed skill by name. |
Recipes
Our own notes on combining the commands above. Every token used here appears in the reference tables on this page.
Drive Hermes tool calling from your own runtime
<tools> in system → model emits <tool_call> → return <tool_response>
The three-tag protocol is the whole loop: definitions in, JSON call out, result back in a tool role message. It is model-level, so it works the same whether Hermes 4 is served locally or through a hosted endpoint.
Frequently Asked Questions
How do I turn on reasoning mode in Hermes 4?
Pass thinking=True to the tokenizer chat template, or use the official deep-thinking system prompt from the model card. Reasoning arrives inside <think> </think> tags; strip them for the final answer.
How does Hermes 4 do function calling?
Tool signatures go inside <tools> </tools> tags in the system message. The model emits calls inside <tool_call> </tool_call> as JSON, and you return results inside <tool_response> </tool_response> in a tool role message.
Which prompt format does Hermes 4 405B use?
The Llama 3.1 header-token format: <|start_header_id|>role<|end_header_id|> with <|eot_id|> closing each turn. Smaller Hermes 4 models use ChatML.
Every entry on this page is a literal, typeable token taken from the official documentation linked above. Command sets in AI tools change quickly - the in-product command menu is always authoritative for your installed version.