RepoRadar hands-on verification log run_id: cohort-20260712-github-copilot-isolated-help entity_id: commercial:github-copilot mode: isolated_npm started_at: 2026-07-13T11:47:42.096685Z completed_at: 2026-07-13T11:47:44.798456Z duration_seconds: 2.702 installation_setup_minutes_ceiling: 1 command: "C:\Program Files\nodejs\npx.CMD" --yes @github/copilot@1.0.70 help credential_policy: child environment allowlisted; credential-like variables excluded; known token patterns redacted from retained output network_policy: isolated package resolution may contact package registries; telemetry and Promptfoo sharing disabled; no model/provider credentials supplied fixture_count: 0 artifact_expectation_count: 0 timeout_seconds: 180 timed_out: false exit_code: 0 expected_marker: none expected_marker_observed: true result: partial cleanup: Per-check temporary home and work directory removed. ===== FIXTURE MANIFEST ===== ===== ARTIFACT EVIDENCE ===== ===== STDOUT ===== Usage: copilot [options] [command] GitHub Copilot CLI - An AI-powered coding assistant. Start an interactive session to chat with Copilot, or use -p/--prompt for non-interactive scripting. Copilot can edit files, run shell commands, search your codebase, and more — all with configurable permissions. Run `copilot --help` for details on any subcommand. Options: --acp Start as Agent Client Protocol server --add-dir Add a directory to the allowed list for file access (can be used multiple times) --add-github-mcp-tool Add a tool to enable for the GitHub MCP server instead of the default CLI subset (can be used multiple times). Use "*" for all tools. --add-github-mcp-toolset Add a toolset to enable for the GitHub MCP server instead of the default CLI subset (can be used multiple times). Use "all" for all toolsets. --additional-mcp-config Additional MCP servers configuration as JSON string or file path (prefix with @) (can be used multiple times; augments config from ~/.copilot/mcp-config.json for this session) --agent Specify a custom agent to use --allow-all Enable all permissions (equivalent to --allow-all-tools --allow-all-paths --allow-all-urls) --allow-all-mcp-server-instructions Include initialization instructions from all MCP servers in the system prompt instead of only allowlisted servers --allow-all-paths Disable file path verification and allow access to any path --allow-all-tools Allow all tools to run automatically without confirmation; required for non-interactive mode (env: COPILOT_ALLOW_ALL) --allow-all-urls Allow access to all URLs without confirmation --allow-tool[=tools...] Tools the CLI has permission to use; will not prompt for permission --allow-url[=urls...] Allow access to specific URLs or domains --attachment Attach a file (image or native document) to the initial prompt; only valid in non-interactive mode (can be used multiple times) --autopilot Start in autopilot mode --available-tools[=tools...] Only these tools will be available to the model --banner Show the startup banner --bash-env[=value] Enable BASH_ENV support for bash shells (on|off) -C Change working directory before doing anything else --connect[=sessionId] Connect directly to a remote session (optionally specify session ID or task ID) --context Set the context window tier (overrides persisted setting) (choices: "default", "long_context") --continue Resume the most recent session --deny-tool[=tools...] Tools the CLI does not have permission to use; will not prompt for permission --deny-url[=urls...] Deny access to specific URLs or domains, takes precedence over --allow-url --disable-builtin-mcps Disable all built-in MCP servers (currently: github-mcp-server) --disable-mcp-server Disable a specific MCP server (can be used multiple times) --disallow-temp-dir Prevent automatic access to the system temporary directory --effort, --reasoning-effort Set the reasoning effort level (choices: "none", "minimal", "low", "medium", "high", "xhigh", "max") --enable-all-github-mcp-tools Enable all GitHub MCP server tools instead of the default CLI subset. Overrides --add-github-mcp-toolset and --add-github-mcp-tool options. --enable-memory Enable memory in prompt mode (disabled by default) --enable-reasoning-summaries Request reasoning summaries for OpenAI models --excluded-tools[=tools...] These tools will not be available to the model --experimental Enable experimental features --extension-sdk-path Override the bundled @github/copilot-sdk injected into extension subprocesses with a local `copilot-sdk/` folder. Invalid paths fall back to the bundled SDK. -h, --help display help for command -i, --interactive Start interactive mode and automatically execute this prompt --log-dir Set log file directory (default: ~/.copilot/logs/) --log-level Set the log level (choices: "none", "error", "warning", "info", "debug", "all", "default") --max-ai-credits Set max AI credits for this session --max-autopilot-continues Maximum number of continuation messages in autopilot mode (default: 5) --mode Set the initial agent mode (choices: "interactive", "plan", "autopilot") --model Set the AI model to use (use 'auto' to let Copilot pick automatically) --mouse[=value] Enable mouse support in alt screen mode (on|off) -n, --name Set a name for the new session --no-ask-user Disable the ask_user tool (agent works autonomously without asking questions) --no-auto-update Disable downloading CLI update automatically (disabled by default in CI environments) --no-bash-env Disable BASH_ENV support for bash shells --no-color Disable all color output --no-custom-instructions Disable loading of custom instructions from AGENTS.md and related files --no-experimental Disable experimental features --no-mouse Disable mouse support in alt screen mode --no-remote Disable remote control of your session from GitHub web and mobile --no-remote-export Disable exporting your session to GitHub web and mobile (also disables remote control) --output-format Output format: 'text' (default) or 'json' (JSONL, one JSON object per line) (choices: "text", "json") -p, --prompt Execute a prompt in non-interactive mode (exits after completion) --plain-diff Disable rich diff rendering (syntax highlighting via diff tool specified by git config) --plan Start in plan mode --plugin-dir Load a plugin from a local directory (can be used multiple times) -r, --resume[=value] Resume from a previous session (optionally specify existing session ID, task ID, ID prefix, or name; name matching is exact, case-insensitive) --remote Enable remote control of your session from GitHub web and mobile --remote-export Export your session to GitHub web and mobile (read-only; does not enable remote control) -s, --silent Output only the agent response (no stats), useful for scripting with -p --screen-reader Enable screen reader optimizations --secret-env-vars[=vars...] Environment variable names whose values are stripped from shell and MCP server environments and redacted from output (e.g., --secret-env-vars=MY_KEY,OTHER_KEY) --session-id Resume an existing session or task by ID, or set the UUID for a new session --share[=path] Share session to markdown file after completion in non-interactive mode (default: ./copilot-session-.md) --share-gist Share session to a secret GitHub gist after completion in non-interactive mode --stream Enable or disable streaming mode (choices: "on", "off") -v, --version show version information --yolo Enable all permissions (equivalent to --allow-all-tools --allow-all-paths --allow-all-urls) Commands: completion Generate a shell completion script help [topic] Display help information init Initialize Copilot instructions login [options] Authenticate with Copilot mcp Manage MCP servers plugin Manage plugins plugins Inspect configured plugins across kinds skill Manage skills update [channel] Download the latest version version Display version information Help Topics: billing AI credit usage commands Interactive Mode Commands config Configuration Settings environment Environment Variables limits Session Limits Controls logging Logging monitoring Monitoring with OpenTelemetry permissions Permissions providers Custom Model Providers (BYOK) Examples: # Start interactive mode $ copilot # Start interactive mode and automatically execute a prompt $ copilot -i "Fix the bug in main.js" # Execute a prompt in non-interactive mode (exits after completion) $ copilot -p "Fix the bug in main.js" --allow-all-tools # Enable all permissions with a single flag $ copilot -p "Fix the bug in main.js" --allow-all $ copilot -p "Fix the bug in main.js" --yolo # Start with a specific model $ copilot --model gpt-5.4 # Resume the most recent session $ copilot --continue # Resume a previous session using session picker $ copilot --resume # Resume a specific session by ID $ copilot --resume= # Name a new session $ copilot --name="my feature" # Start a new session with a specific UUID $ copilot --session-id=0cb916db-26aa-40f2-86b5-1ba81b225fd2 # Resume or attach to an existing session or task by ID $ copilot --session-id= # Resume a session by name $ copilot --resume="my feature" # Resume a session by ID prefix (7+ hex chars) $ copilot --resume=0cb916d # Resume with auto-approval $ copilot --allow-all-tools --resume # Allow access to additional directory $ copilot --add-dir /home/user/projects # Allow multiple directories $ copilot --add-dir ~/workspace --add-dir /tmp # Disable path verification (allow access to any path) $ copilot --allow-all-paths # Allow all git commands except git push $ copilot --allow-tool='shell(git:*)' --deny-tool='shell(git push)' # Allow all file editing $ copilot --allow-tool='write' # Allow all but one specific tool from MCP server with name "MyMCP" $ copilot --deny-tool='MyMCP(denied_tool)' --allow-tool='MyMCP' # Allow GitHub API access (defaults to HTTPS) $ copilot --allow-url=github.com # Deny access to specific domain over HTTPS $ copilot --deny-url=https://malicious-site.com $ copilot --deny-url=malicious-site.com # Allow all URLs without confirmation $ copilot --allow-all-urls # Initialize Copilot instructions for a repository $ copilot init Learn More: Use `copilot --help` for more information about a command. Read the documentation at https://docs.github.com/copilot/how-tos/copilot-cli ===== STDERR ===== cohort_cache_cleanup: Shared cohort package cache removed. bounded_workflow_intended: false bounded_workflow_completed: false