> ## Documentation Index
> Fetch the complete documentation index at: https://comis-feature-matrix-channel.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Slash Commands
> All the commands you can type to control your agent
Slash commands let you control your agent directly from the chat. Type a
command starting with `/` and your agent will act on it instead of treating
it as a regular message.
## Quick reference
Here is the complete list of all 17 commands:
| Command | What it does | Example |
| ----------------------------------- | ------------------------------------------------------------------------------------------ | ---------------------------------------------------- |
| `/think [level]` | Set reasoning depth (off, minimal, low, medium, high, xhigh) | `/think high` |
| `/verbose [on\|off]` | Toggle detailed output | `/verbose on` |
| `/reasoning [on\|off]` | Show or hide the reasoning process | `/reasoning on` |
| `/context` | Show context window usage and file sizes | `/context` |
| `/status` | Show session info, message count, model, tokens used, cost | `/status` |
| `/usage` | Show per-provider token and cost breakdown | `/usage` |
| `/config` | Show current agent configuration | `/config` |
| `/model list\|switch\|cycle` | List available models, switch model, or cycle through them | `/model switch anthropic claude-sonnet-4-5-20250929` |
| `/new` | Start a fresh conversation (new session) | `/new` |
| `/reset` | Reset current session (clear history) | `/reset` |
| `/compact [verbose] [instructions]` | Manually trigger context compaction | `/compact` |
| `/export [path]` | Export session to HTML file | `/export ~/chat.html` |
| `/export-trajectory` | Export a trajectory bundle for the current session (trace, context, and artifact snapshot) | `/export-trajectory` |
| `/stop` | Cancel current agent execution | `/stop` |
| `/fork` | Fork conversation at your latest message | `/fork` |
| `/branch [list\|target-id]` | List branch points or navigate to one | `/branch list` |
| `/budget [amount]` | Set per-execution token budget for the next message (`Nk` or `Nm`) | `/budget 500k` |
| `/skill:name [args]` | Invoke a prompt skill by name | `/skill:weather London` |
## Command categories
### Thinking controls
**Commands:** `/think`, `/verbose`, `/reasoning`
These are *directive* commands -- they modify how your agent processes your
message rather than being separate actions. When you use a directive, the
command is stripped from your text before your agent sees it. Your agent never
sees the `/think` part -- it just receives your message with the thinking level
already adjusted.
#### /think
Controls how deeply your agent reasons about its response. Higher levels mean
more thorough thinking, which can improve answer quality for complex questions
but uses more tokens.
| Level | What it means |
| --------- | ------------------------------------------------ |
| `off` | No extended thinking -- fastest, cheapest |
| `minimal` | Light reasoning for simple tasks |
| `low` | Basic reasoning for straightforward questions |
| `medium` | Balanced reasoning for most tasks |
| `high` | Deep reasoning for complex problems |
| `xhigh` | Maximum reasoning depth for the hardest problems |
Without an argument, `/think` toggles thinking on or off.
#### /verbose
Toggles detailed output. When enabled, your agent includes more information
in its responses -- useful for debugging or understanding its decision-making.
#### /reasoning
Shows or hides the reasoning process. When enabled, you can see how your
agent arrived at its answer, including its internal thought steps.
### Information
**Commands:** `/context`, `/status`, `/usage`, `/config`
Read-only commands that show you what is happening. None of these change
anything -- they just report on the current state.
#### /context
Shows how much of the context window your agent is using. This includes the
sizes of workspace files, tool definitions, and conversation history. Useful
for understanding why your agent might be forgetting earlier parts of a long
conversation.
#### /status
Shows session details: how many messages have been exchanged, which model is
active, how many tokens have been used, and the estimated cost so far.
#### /usage
Shows a breakdown of token usage and costs per provider. If you are using
multiple models or providers, this helps you understand where your budget is
going.
#### /config
Displays the current agent configuration: name, model, provider, max steps,
and other active settings.
### Model switching
**Commands:** `/model`
The `/model` command has three sub-commands:
| Sub-command | What it does | Example |
| ----------- | ---------------------------------------- | ---------------------------------------------------- |
| `list` | Shows all available models and providers | `/model list` |
| `switch` | Changes the model for this session | `/model switch anthropic claude-sonnet-4-5-20250929` |
| `cycle` | Rotates through configured models | `/model cycle` |
The `switch` sub-command takes two arguments: the provider name and the model
identifier. The change applies only to the current session -- it does not
modify your configuration file.
### Session management
**Commands:** `/new`, `/reset`, `/compact`, `/export`
These commands manage your conversation state:
#### /new
Starts a completely fresh conversation. Your agent gets a new session with
no history. This is useful when you want to change topics entirely or start
from a clean slate.
#### /reset
Clears the history of the current session but keeps the same session
identifier. Your agent forgets what was said in this conversation but stays
in the same session context.
#### /compact
Manually triggers the context engine's LLM compaction step. When your
conversation gets long, this command summarizes older messages to free up space
in the context window. Normally, the context engine manages conversation length
automatically through multiple optimization steps (see
[Compaction](/agents/compaction)), but you can trigger the summarization step
directly if you want to reclaim space sooner.
Optional arguments:
* `verbose` -- Include detailed output about what was compacted
* Any additional text is used as instructions for the compaction summary
#### /export
Exports the current session to an HTML file. Optionally specify a file path
(defaults to a generated path in your home directory).
### Execution control
**Commands:** `/stop`
Cancels the current agent execution. If your agent is taking too long, going
in the wrong direction, or stuck in a tool loop, `/stop` immediately halts
the current run. The session remains intact -- you can continue chatting
normally after stopping.
### Branching
**Commands:** `/fork`, `/branch`
These commands let you explore different conversation paths, like a "what if"
feature for your chats.
#### /fork
Creates a copy of your conversation at your latest message. This lets you
try a different approach without losing the original conversation. Think of it
as going back to the last thing you said and asking for a different response.
#### /branch
Navigates between conversation branches.
| Usage | What it does |
| --------------------- | ------------------------------------------------------ |
| `/branch list` | Shows all available branch points in your conversation |
| `/branch [target-id]` | Jumps to a specific branch point |
After forking, you can use `/branch list` to see all the points where you
branched off, and `/branch [id]` to jump back to any of them.
### Budget control
**Command:** `/budget`
The `/budget` command sets a per-execution token budget for the next agent run. The amount must be a number with a `k` (thousands) or `m` (millions) suffix; bare integers are not accepted. Valid range is 10k to 10m tokens.
| Usage | Effect |
| -------------- | ------------------------------------------------------ |
| `/budget 500k` | Set the next execution to use at most 500,000 tokens |
| `/budget 2m` | Set the next execution to use at most 2,000,000 tokens |
| `/budget` | Show usage help and the configured range |
You can also use the inline form `+500k` or `+2m` at the start or end of a message (e.g., `+500k research the topic`).
Like `/think` and `/verbose`, `/budget` is a *directive* command -- it modifies how your agent processes the next message rather than being a separate action.
### Skills
**Commands:** `/skill:name`
Custom prompt skills can be invoked directly from the chat using the
`/skill:skillname` syntax. The skill name comes after the colon, and any
text after the name is passed as arguments.
For example, if you have a prompt skill called `weather`:
```
/skill:weather London
```
This invokes the `weather` skill with "London" as the argument. The skill's
prompt template is expanded and used to guide your agent's response.
See [Prompt Skills](/skills/prompt-skills) for how to create and manage
custom skills.
## Combining directives with messages
Directive commands (`/think`, `/verbose`, `/reasoning`) can be combined with
a regular message. For example:
`/think high Tell me about quantum computing`
This sets reasoning to high AND sends the message "Tell me about quantum
computing" to your agent. The directive is stripped before your agent sees
the text.
This works because directives modify the *processing* of your message, not the
message itself. Other commands (like `/status` or `/new`) are standalone -- they
do not accept additional message text.
## How commands are recognized
Slash commands are only recognized when your message *starts* with the `/`
character. If you write a `/` in the middle of a sentence, it is treated as
regular text. This means you can safely type things like "I need help with
my /home directory" without triggering a command.
Commands are not case-sensitive for the `/skill:` prefix (`/Skill:weather` and
`/skill:Weather` both work), but the built-in command names must be lowercase
(`/think`, not `/Think`).
If you type an unrecognized command (for example, `/hello`), it is treated as
a regular message and passed to your agent as-is. Only the 17 built-in
commands and the `/skill:name` prefix have special behavior.
Slash commands work on every platform -- Discord, Telegram, Slack, WhatsApp,
the web dashboard, and all other connected channels. They are processed by
Comis before reaching your agent, so the platform does not need to support
slash commands natively.
How conversations are tracked and managed.
Choosing AI providers and switching models.
Create custom skills your agent can invoke.