This document provides a comprehensive guide to all available slash commands in Plexir.
Displays a summary of all primary slash commands.
Opens an interactive model picker to switch the active provider and model globally. This updates your config.json and reloads providers.
Toggles YOLO mode (autonomous mode).
/yolo start: Disables safety confirmations for critical tools./yolo stop: Enables safety confirmations (default).
Clears the chat display and current conversation history. This cannot be undone.
Lists all tools currently registered and available to the AI agent.
Forces a reload of all provider configurations from ~/.plexir/config.json. Useful after manually editing the config file.
Exits the Plexir application cleanly, stopping the sandbox if it's running.
Manages providers, tool settings, and application preferences.
Shows the current provider failover order, tool configurations, and other app settings.
Updates a specific property for a provider.
<provider_name>: The name of the provider (e.g.,"Gemini Primary"). Use quotes if it contains spaces.<key>: The property to change (api_key,model_name,type,base_url,context_limit).<value>: The new value.- Example:
/config set "Gemini Primary" context_limit 50000 - Example:
/config set "Groq Backup" model_name llama3-70b-8192
Sets a maximum dollar amount for the current session to prevent runaway costs.
- Example:
/config budget 0.50 - Example:
/config budget 0(disables limit)
Sets the application verbosity level for tool outputs.
0: Normal (truncated tool outputs, concise logs).1: Verbose (full tool outputs, more detailed logs).2: Debug (maximum detail for troubleshooting).- Example:
/config verbosity 1
Toggles whether "Thinking" blocks (reasoning process) are expanded or collapsed by default in the chat.
- Example:
/config reasoning off
Sets a configuration value for a specific tool suite. This is how you provide tokens for external services.
<domain>: The tool domain (e.g.,git,github).<key>: The configuration key (e.g.,token,allowed_repos).<value>: The configuration value.- Example (Git PAT):
/config tool git token ghp_... - Example (GitHub Permissions):
/config tool github token ghp_... - Example (GitHub Permissions):
/config tool github allowed_repos pomilon/plexir,another/repo - Example (Web Search):
/config tool web tavily_api_key tvly-XXXX - Example (Web Search):
/config tool web serper_api_key XXXX
Adds a new LLM provider.
<name>: A unique name (e.g.,"My OpenAI").<type>: Provider type (openai,gemini,groq,ollama,mcp).<model>: The model identifier (e.g.,gpt-4o,gemini-1.5-pro-latest).[options]: Optionalapi_key=...andbase_url=...for self-hosted models.- Example:
/config add "Local LLM" ollama llama3 base_url=http://localhost:11434
Removes a provider from your configuration.
- Example:
/config delete "Groq Backup"
Changes the failover priority of a provider.
- Example:
/config reorder "Local LLM" up
Saves and loads chat histories.
Lists all saved session files.
Saves the current conversation history to a file. If [name] is omitted, a timestamp is used.
Note: This also saves the current scratchpad state associated with this session name.
- Example:
/session save my-feature-dev
Clears the current chat and loads a saved session.
Note: This also loads the scratchpad associated with the session name, ensuring planning continuity.
- Example:
/session load my-feature-dev
Deletes a saved session file.
- Example:
/session delete old-session
Records and plays back sequences of commands and prompts.
Starts recording all subsequent inputs into a macro named <name>.
- Example:
/macro record setup-env
Stops the current recording and saves the macro.
Executes all the commands from a saved macro in sequence.
- Example:
/macro play setup-env
Lists all saved macros.
Deletes a saved macro.
- Example:
/macro delete old-macro