Skip to main content
Devin for Terminal is designed to be deeply customizable. You can shape how the agent behaves, what tools it has access to, and how it responds to events — all through configuration files in your project or home directory.

How It All Fits Together

These features work at different layers:
  • Rules shape the agent’s personality and constraints — they’re always active.
  • Skills give the agent new capabilities it can invoke on demand.
  • MCP Servers provide entirely new tools the agent can call.
You can combine all of these in a single project. For example, you might have an AGENTS.md file with coding standards, a review skill for code review, and an MCP server for your issue tracker.

Where Configuration Lives

All project-level extensibility configuration lives in the .cognition/ directory at your project root:
my-project/
├── .cognition/
│   ├── config.json          # Project config (MCP, permissions)
│   ├── config.local.json    # Personal overrides (gitignored)
│   └── skills/
│       └── review/
│           └── SKILL.md     # A custom skill
├── AGENTS.md                # Project rules
└── src/
User-level configuration lives in ~/.config/cognition/ and applies to all projects.
Files with .local. in the name are automatically excluded from git, so you can have personal overrides without affecting your team.

Importing From Other Tools

Devin for Terminal can read configuration from other AI coding tools you may already use:
SourceWhat’s Imported
AGENTS.md / AGENT.md / CLAUDE.mdRules (always-on context)
.cursor/rules/*.md / .cursorrulesRules
.windsurf/rules/*.mdRules
.claude/ directoryCommands
This means you can start using Devin for Terminal without rewriting your existing configuration. Import is enabled by default and can be controlled in your config file:
{
  "read_config_from": {
    "cursor": true,
    "windsurf": true,
    "claude": true
  }
}
Set any provider to false to disable importing from it.