For a complete list of available slash commands enter /help in the CLI's interactive interface.

For a complete list of commands and options, run copilot help.

The --allow-tool and --deny-tool options accept permission patterns in the format Kind(argument). The argument is optional—omitting it matches all tools of that kind.

For shell rules, the :* suffix matches the command stem followed by a space, preventing partial matches. For example, shell(git:*) matches git push and git pull but does not match gitea.

Deny rules always take precedence over allow rules, even when --allow-all is set.

# Allow all git commands except git push
copilot --allow-tool 'shell(git:*)' --deny-tool 'shell(git push)'

# Allow a specific MCP server tool
copilot --allow-tool 'MyMCP(create_issue)'

# Allow all tools from a server
copilot --allow-tool 'MyMCP'

User settings are stored in ~/.copilot/config.json. Project-level settings can be placed in .copilot/settings.json (committed to the repository) or .copilot/settings.local.json (personal overrides—add to .gitignore). Settings cascade from user to project to local, with more specific scopes overriding more general ones. Command-line flags and environment variables always take the highest precedence.

Hooks are external commands that execute at specific lifecycle points during a session, enabling custom automation, security controls, and integrations. Hook configuration files are loaded automatically from .github/hooks/*.json in your repository.

Hook configuration files use JSON format with version 1:

{
  "version": 1,
  "hooks": {
    "preToolUse": [
      {
        "type": "command",
        "bash": "your-bash-command",
        "powershell": "your-powershell-command",
        "cwd": "optional/working/directory",
        "env": { "VAR": "value" },
        "timeoutSec": 30
      }
    ]
  }
}

The preToolUse hook can control tool execution by writing a JSON object to stdout.

If multiple hooks of the same type are configured, they execute in order. For preToolUse, if any hook returns "deny", the tool is blocked. Hook failures (non-zero exit codes or timeouts) are logged and skipped—they never block agent execution.

MCP servers provide additional tools to the CLI agent. Configure persistent servers in ~/.copilot/mcp-config.json. Use --additional-mcp-config to add servers for a single session.

Control how MCP tool output is processed using the filterMapping field in a server's configuration.

The CLI includes built-in MCP servers that are available without additional setup.

Use --disable-builtin-mcps to disable all built-in servers, or --disable-mcp-server SERVER-NAME to disable a specific one.

Skills are Markdown files that extend what the CLI can do. Each skill lives in its own directory containing a SKILL.md file. When invoked (via /SKILL-NAME or automatically by the agent), the skill's content is injected into the conversation.

Skills are loaded from these locations in priority order (first found wins for duplicate names).

Commands are an alternative to skills stored as individual .md files in .claude/commands/. The command name is derived from the filename. Command files use a simplified format (no name field required) and support description, allowed-tools, and disable-model-invocation. Commands have lower priority than skills with the same name.

Custom agents are specialized AI agents defined in Markdown files. The filename (minus extension) becomes the agent ID. Use .agent.md or .md as the file extension.

Project-level agents take precedence over user-level agents. Plugin agents have the lowest priority.

When the CLI prompts for permission to execute an operation, you can respond with the following keys.

Session approvals reset when you run /clear or start a new session.