Made Shop

Acknowledge platform start pings without a reply

/profile

Show active profile name and home directory

/model

Switch model (session-scoped; --global to persist)

/yolo

Toggle YOLO mode (skip all dangerous command approvals)

/whoami

Show your slash command access (admin / user)

/airtable

Airtable REST API via curl. Records C...

/footer

Toggle gateway runtime-metadata footer on final replies

/help

Show available commands

/diff

Show git changes in the working directory

/topic

Enable or inspect Telegram DM topic sessions

/debug

Upload debug report (system info + logs) and get shareable links

/personality

Set a predefined personality

/retry

Retry the last message (resend to agent)

/status

Show session, model, token, and context info

/codex_runtime

Toggle codex app-server runtime for OpenAI/Codex models

/undo

Back up N user turns and re-prompt (default 1)

/reload_mcp

Reload MCP servers from config

/sethome

Set this chat as the home channel

/title

Set a title for the current session

/restart

Gracefully restart the gateway after draining active runs

/context

Show detailed context window view with usage gauge, category breakdown, compression stats, and throughput

/branch

Branch the current session (explore a different path)

/arxiv

Search arXiv papers by keyword, autho...

/subgoal

Add or manage extra criteria on the active goal

/compress

Compress conversation context (add 'here [N]' to keep recent N turns; --preview shows what would happen)

/kanban

Multi-profile collaboration board (tasks, links, comments)

/moa

Run one prompt through the default Mixture of Agents preset, then restore your model

/rollback

List or restore filesystem checkpoints

/update

Update Hermes Agent to the latest version

/goal

Set a standing goal Hermes works on across turns until achieved

/agents

Show active agents and running tasks

/version

Show Hermes Agent version

/curator

Background skill maintenance (status, run, pin, archive, list-archived)

/commands

Browse all commands and skills (paginated)

/egress

Show Docker egress proxy status

/blueprint

Set up an automation from a blueprint template

/approve

Approve a pending dangerous command

/architecture_diagram

Dark-themed SVG architecture/cloud/in...

/suggestions

Review suggested automations (accept/dismiss)

/deny

Deny a pending dangerous command (optionally with a reason)

/insights

Show usage insights and analytics

/init

Generate or update AGENTS.md project instructions from a repo scan

/queue

Queue a prompt for the next turn (doesn't interrupt)

/resume

Resume a previously-named session

/learn

Learn a reusable skill from anything you describe (dirs, URLs, this chat, notes)

/steer

Inject a message after the next tool call without interrupting

/stop

Kill all running background processes

/bundles

List skill bundles (aliases /<name> for multiple skills)

/background

Run a prompt in the background

/topup

Show your Nous balance and manage billing on the portal

/memory

Review pending memory writes / toggle the approval gate

/reasoning

Manage reasoning effort and display

/sessions

Browse and resume previous sessions

/voice

Toggle voice mode

/usage

Show token usage and rate limits; `reset` redeems a banked Codex limit reset

/new

Start a new session (fresh session ID + history)

/fast

Toggle fast mode — OpenAI Priority Processing / Anthropic Fast Mode (Normal/Fast)

/platform

Pause, resume, or list a failing gateway platform

/reload_skills

Re-scan ~/.hermes/skills/ for newly installed or removed skills

/approvals

Show or set the persistent dangerous-command approval mode