Security & Privacy

Command Code is designed with security and privacy as core principles. Your code stays yours — we never train on it, and you control exactly what Command Code can access.


WhatStored?WhereUsed for training?
Source codeNever storedYour machine onlyNo
Taste profileLocal + optional cloud sync.commandcode/taste/ and commandcode.aiNo
Conversation historyLocal only~/.commandcode/projects/No
Authentication tokensLocal only~/.commandcode/auth.jsonNo
AGENTS.mdLocal onlyProject rootNo
Privacy

Command Code does not train on your code. Taste learning runs locally and stores preferences as structured rules — not code snippets.


Command Code uses a permission system that puts you in control of every action. By default, any action that modifies your system requires explicit approval.

Permission Modes

ModeFile readsFile writesShell commandsWhen to use
DefaultAllowedRequires approvalRequires approvalDay-to-day work
PlanAllowedBlockedBlockedExploring and designing
Auto-AcceptAllowedAllowedAllowedTrusted iteration

Switch modes with shift+tab inside a session, or start with a specific mode:

cmd --plan # Start in plan mode cmd --auto-accept # Start in auto-accept mode cmd --permission-mode auto-accept # Start in auto-accept mode (long form)

Project Trust

The first time you run cmd in a project, Command Code asks whether to trust that directory. This prevents accidental execution in untrusted locations.

cmd --trust # Skip the trust prompt

When running in headless mode (cmd -p), all write operations are blocked by default. This keeps CI/CD pipelines and scripts safe.

To enable writes in headless mode, you must explicitly pass:

cmd -p "fix lint errors" --yolo

--dangerously-skip-permissions is also accepted as an alias.

Warning

Only use --yolo in trusted environments like your own CI pipelines. It allows Command Code to modify files and run shell commands without confirmation.


Command Code connects to the internet for:

  • API requests to the AI provider (Command Code or Anthropic)
  • Authentication via OAuth (during cmd login)
  • Taste sync when you push/pull taste profiles
  • MCP servers you explicitly configure

Command Code does not make any network requests for telemetry or tracking without your knowledge. See Telemetry for details on what optional telemetry is collected and how to opt out.


Command Code only accesses files within:

  1. Your current project directory (where you ran cmd)
  2. Additional directories you explicitly add with --add-dir or /add-dir
  3. Command Code config in ~/.commandcode/

It does not read files outside these boundaries.


Authentication credentials are stored locally at ~/.commandcode/auth.json. They are never sent to any third party.

If you use BYOK (Bring Your Own Key) with Anthropic, your API key is stored in your environment variables — Command Code does not persist it.


When connecting MCP servers, be aware that:

  • MCP tools can access external services (databases, APIs, etc.)
  • Each MCP server connection requires explicit setup via cmd mcp add
  • OAuth tokens for MCP servers are stored locally
  • You can review connected servers anytime with cmd mcp list or /mcp

Only connect MCP servers you trust.


Command Code creates checkpoints before every file modification. If anything goes wrong, you can instantly rewind to a previous state.

  • Press Esc twice to open the checkpoint selector
  • Restore files, conversation, or both
  • Checkpoints are stored locally and per-session

For organizations with stricter requirements, Command Code Enterprise offers:

  • Self-hosted deployment options
  • Your code never leaves your infrastructure
  • Custom security policies

Contact support@commandcode.ai for details.