Skip to main content
Agent Mode transforms ChatCLI from a passive assistant into a proactive executor. Delegate a complete task, and the AI creates, presents, and — with your approval — executes an action plan.

​
How to Start

Use /agent or /run, followed by your task in natural language: 
/agent find all log files modified in the last 24h and copy them to 'recent_logs'
The AI will respond with an Action Plan: a list of structured commands for review.

​
The Agent Cycle

​
Action Plan Interface

After planning, you will see a dedicated screen with two views (toggle with p):
Ideal for an overview of the flow, showing status and the first line of each command.
PLAN (compact view)
  #1: Create the destination directory -- mkdir -p recent_logs
  #2: Find and copy the files -- find ~ -name "*.log" -mtime -1 -exec cp {} recent_logs/ \;

​
Interactive Menu

The menu allows you to manage execution with precision:
ActionDescription
[N]Execute Command N — runs a single step of the plan (e.g., 1)
aExecute All — runs all pending commands in sequence
eNEdit Command N — opens the command in an editor for modification
tNTest (Dry-Run) — simulates execution without making changes
cNContinue from N — sends the output to the AI and asks for next steps
pcNPre-Execution Context — adds information for the AI to refine the command
acNPost-Execution Context — sends the output with new context
vNView Output — opens the full output in a pager (less)
wNSave Output — saves the command output to a temporary file
pToggle Plan — switches between compact and full view
rRedraw Screen — clears the screen
qQuit — exits Agent Mode and returns to chat
Use tN (test) to verify what a command will do. If it looks good, execute with N. If something goes wrong, use cN to ask the AI to fix the plan.

​
Security

Dangerous commands (rm -rf, sudo, mkfs, dd) are blocked by default. ChatCLI will require explicit confirmation before allowing their execution.
You always have the final say. No command is executed without your approval.

​
Unified History and Context

Agent mode shares the same conversation history as chat and coder. This means you can:
  • Start a conversation in chat, enter /agent, and the AI will have all the previous context
  • Use /compact to reduce history when it gets large
  • Use /rewind (or Esc+Esc) to go back to an earlier point in the conversation
Additionally, the agent automatically receives workspace context (bootstrap files like SOUL.md, USER.md, and persistent memory) in its system prompt.

​
Next Steps

Coder Mode

AI that reads, edits, and tests code in an automated loop.

Conversation Control

Use /compact and /rewind to manage history.

Session Management

Save and reuse your work across projects.