dcode) accepts command-line flags at launch and exposes management subcommands for agents, sessions, skills, credentials, and configuration. Use this page as a reference when you need to override defaults from the shell, run non-interactive tasks in scripts, or automate administration without opening a session. For installation and daily interactive use, see Quickstart. For how CLI flags fit into the broader configuration model, see Configuration.
Example usage
Choose a model
Launch with--model (-M) to pin a model for one session. Use the provider:model format (for example, openai:gpt-5.5) or pass a bare model name when the provider is unambiguous:
--model, it resolves the model in this order:
--modelflag when provided.[models].defaultin~/.deepagents/config.toml.[models].recentin~/.deepagents/config.toml(written automatically when you switch models in a session).- Environment auto-detection: the first available credential among
OPENAI_API_KEY,ANTHROPIC_API_KEY,GOOGLE_API_KEY, andGOOGLE_CLOUD_PROJECT(Vertex AI).
--model or saved defaults even though they are not part of the startup auto-detection list. See Model providers for the full provider list and credential setup.
Set or clear a default model
Persist a default model for all future launches:/model switcher (Ctrl+S) or set [models].default in config.toml. See Set a default model.
Model parameters and profile overrides
Pass extra constructor kwargs to the model with--model-params as a JSON string. These apply for the current session only and override config.toml provider params:
max_input_tokens) with --profile-override. Values merge on top of config file overrides and persist across mid-session /model hot-swaps:
--max-retries or the [retries] section in config.toml. See Model parameters and Profile overrides.
Install provider extras
Optional provider and sandbox packages ship as extras. Install from the shell without launching a session:--package to install an arbitrary provider package via uv --with (see Arbitrary providers), and --yes to skip confirmation prompts. To preinstall extras during the initial CLI install, set DEEPAGENTS_CODE_EXTRAS (for example, DEEPAGENTS_CODE_EXTRAS="groq,fireworks").
Agents and sessions
Use-a/--agent to launch with a named agent that has its own memory, skills, and AGENTS.md under ~/.deepagents/<agent_name>/. The flag overrides both [agents].default and [agents].recent in config.toml:
-r/--resume. Pass no ID to open the most recent thread, or pass a thread ID to resume a specific session. Resuming bypasses agent selection flags and restores the thread’s original agent:
dcode threads list and dcode threads delete. See Memory and skills for how per-agent memory works.
Non-interactive mode and piping
Use-n/--non-interactive to run a single task without the interactive UI. Each non-interactive run starts a fresh thread; file-based state (memory, skills, configuration) persists across invocations:
-n or -m, the piped content appears first, followed by the flag text. The maximum piped input size is 10 MiB. Use --stdin to read from stdin explicitly instead of auto-detection.
Output, limits, and shell access
Use-q/--quiet to emit only the agent’s response on stdout (for piping into other commands). Add --no-stream to buffer the full response before writing:
--max-turns or --timeout. Both exit with code 124 when the budget is exceeded. Requires -n or piped stdin:
-S/--shell-allow-list:
Skills at launch
The--skill flag invokes a skill immediately on launch in interactive or non-interactive mode:
--skill with --quiet or --no-stream requires -n. Manage skills with dcode skills list, create, info, and delete. See Memory and skills.
Rubrics in scripts
Non-interactive runs cannot pause for interactive goal review. Pass acceptance criteria with--rubric when criteria are already known:
-n or piped stdin. See Goals and rubrics.
Human-in-the-loop and shell access
Potentially destructive tool calls require approval by default. Skip prompts for a session with-y/--auto-approve, or toggle auto-approve with Shift+Tab during an interactive session:
-S/--shell-allow-list flag applies in both interactive and non-interactive modes. Pass a comma-separated list of command names, recommended for safe read-only defaults, or all to permit any command. You can also set DEEPAGENTS_CODE_SHELL_ALLOW_LIST in the environment.
Startup commands and initial prompts
Use-m/--message to auto-submit an initial prompt when an interactive session starts. Combine with --startup-cmd to run a shell command first:
--startup-cmd output is rendered in the transcript for your reference but is not added to the agent’s message history. To hand command output to the agent, pipe it via stdin instead:
--startup-cmd warn but do not abort the session. Non-interactive mode applies a 60-second timeout to the startup command.
Remote sandboxes
Route code execution to a remote sandbox with--sandbox. Built-in providers include langsmith, agentcore, daytona, modal, runloop, and vercel. Third-party and config-declared providers are also accepted. Pass --sandbox with no value to use [sandboxes].default from config.toml:
Because
--sandbox accepts an optional value, keep the bare form last on the command line. Otherwise a following argument (for example, dcode --sandbox agents) is consumed as the flag’s value.dcode --install (for example, dcode --install daytona or dcode --install all-sandboxes). See Remote sandboxes for provider setup, working directories, and third-party providers.
MCP flags
Control MCP server loading at launch:| Flag | Behavior |
|---|---|
--mcp-config PATH | Add an explicit config as the highest-precedence source (merged on top of auto-discovered configs) |
--no-mcp | Disable MCP entirely |
--trust-project-mcp | Trust project-level stdio servers without prompting (for CI and automation) |
--mcp-config and --no-mcp are mutually exclusive. In non-interactive mode, project-level stdio servers are silently skipped unless --trust-project-mcp is passed:
auth: "oauth" with dcode mcp login <server>. See MCP tools.
Command-line options
| Option | Description |
|---|---|
-a, --agent NAME | Use named agent with separate memory. Overrides [agents].recent and [agents].default in config.toml. Default: agent (or the most recently used agent if [agents].recent is set) |
-M, --model MODEL | Use a specific model (provider:model) |
--model-params JSON | Extra kwargs to pass to the model as a JSON string (e.g., '{"temperature": 0.7}') |
--max-retries N | Override the max retries for transient model errors |
--default-model [MODEL] | Set the default model (omit MODEL to view the current default) |
--clear-default-model | Clear the default model |
-r, --resume [ID] | Resume a session: -r for most recent, -r <ID> for a specific thread |
-m, --message TEXT | Initial prompt to auto-submit when the session starts (interactive mode) |
--skill NAME | Invoke a skill at startup |
--startup-cmd CMD | Shell command to run at startup, before the first prompt. Output is rendered in the transcript for your reference but is not added to the agent’s message history. To hand command output to the agent, pipe it in via stdin instead (e.g., git diff | dcode -n "Review these changes"). Non-zero exits and timeouts warn but do not abort; non-interactive mode applies a 60s timeout. |
--rubric TEXT|@PATH | Acceptance criteria for rubric grading. Accepts literal text or @path to read a file. Requires -n or piped stdin |
--rubric-model MODEL | Model the rubric grader uses. Defaults to the main agent model. Requires -n or piped stdin |
--rubric-max-iterations N | Grader iterations per rubric attempt before stopping. Requires -n or piped stdin |
-n, --non-interactive TEXT | Run a single task non-interactively and exit. Shell is disabled unless --shell-allow-list is set |
--max-turns N | Cap agentic turns in non-interactive mode. Exits with code 124 when exceeded. Requires -n or piped stdin. See Non-interactive mode and piping |
--timeout SECONDS | Hard wall-clock timeout for non-interactive mode. Exits with code 124 when exceeded. Requires -n or piped stdin. See Non-interactive mode and piping |
-q, --quiet | Clean output for piping—only the agent’s response goes to stdout. Requires -n or piped stdin |
--no-stream | Buffer the full response and write to stdout at once instead of streaming. Requires -n or piped stdin |
--stdin | Read input from stdin explicitly instead of auto-detection. Errors clearly when stdin is unavailable or is a TTY |
-y, --auto-approve | Auto-approve all tool calls without prompting (disables human-in-the-loop). Toggle with Shift+Tab during an interactive session |
-S, --shell-allow-list LIST | Comma-separated shell commands to auto-approve, 'recommended' for safe defaults, or 'all' to allow any command. Applies to both -n and interactive modes |
--json | Emit machine-readable JSON from management subcommands (agents, threads, skills, update). Output envelope: {"schema_version": 1, "command": "...", "data": ...} |
--sandbox TYPE | Remote sandbox for code execution: none (default), langsmith, agentcore, daytona, modal, runloop, vercel, and third-party providers. LangSmith is included; other built-ins require extras. Pass --sandbox with no value to use [sandboxes].default from config |
--sandbox-id ID | Reuse an existing sandbox (skips creation and cleanup) |
--sandbox-snapshot-name NAME | Sandbox snapshot name to use or create (langsmith, runloop, and providers that advertise snapshot support) |
--sandbox-setup PATH | Path to setup script to run in sandbox after creation |
--mcp-config PATH | Add an explicit MCP config as the highest-precedence source (merged with auto-discovered configs) |
--no-mcp | Disable all MCP tool loading |
--trust-project-mcp | Trust project-level MCP configs with stdio servers (skip approval prompt) |
--interpreter | Enable the JS interpreter (js_eval) middleware on the main agent when it has been disabled in config. js_eval is enabled by default. |
--interpreter-tools VALUE | PTC allowlist for js_eval: safe, all, or a comma-separated list of tool names. Default: no PTC (pure REPL) |
--profile-override JSON | Override model profile fields as a JSON string (e.g., '{"max_input_tokens": 4096}'). Merged on top of config file profile overrides |
--acp | Run as an ACP server over stdio instead of launching the interactive UI |
--update | Check for and install updates, then exit |
--auto-update | Toggle automatic updates on or off, then exit |
--install NAME | Install an optional extra (e.g., quickjs, daytona, fireworks), then exit. Add --package to treat NAME as a custom provider package installed via uv --with rather than an extra (see arbitrary providers), and --yes to skip confirmation prompts |
-v, --version | Display version |
-h, --help | Show help |
Manage credentials (dcode auth)
The dcode auth command group is the scriptable equivalent of the /auth credential manager. It reads and writes the same auth.json store without launching the TUI:
set refuses to run in an interactive terminal unless you pipe the key via stdin or use --from-env. dcode auth set manages API keys only; the openai_codex provider uses ChatGPT browser sign-in via /auth instead. See Provider credentials.
Inspect configuration (dcode config)
The dcode config command group reports effective configuration without starting a session. Use it to confirm that an environment variable or config.toml setting is picked up, or to share a redacted snapshot in a bug report:
--json. See Inspect configuration.
Run diagnostics (dcode doctor)
Use dcode doctor when Deep Agents Code is not starting correctly, a provider or MCP server does not connect, tracing is misconfigured, or an install or update looks wrong. It summarizes install method, dependency versions, update status, tracing configuration, and data directory health without launching a session.
Pair dcode doctor with dcode config show when you need both a high-level health check and the exact source of a specific setting. See Run diagnostics with dcode doctor.
CLI commands
| Command | Description |
|---|---|
dcode help | Show help |
dcode agents list | List all agents (alias: ls) |
dcode agents reset --agent NAME | Clear agent memory and reset to default. Supports --dry-run |
dcode agents reset --agent NAME --target SOURCE | Copy memory from another agent |
dcode update | Check for and install Deep Agents Code updates |
dcode doctor | Run diagnostics without launching a session |
dcode skills list [--project] | List all skills (alias: ls) |
dcode skills create NAME [--project] | Create a new skill with template SKILL.md. Idempotent—re-creating an existing skill prints an informational message instead of an error |
dcode skills info NAME [--project] | Show detailed information about a skill |
dcode skills delete NAME [--project] [-f] | Delete a skill and its contents. Supports --dry-run |
dcode threads list [--agent NAME] [--limit N] | List sessions (alias: ls). Default limit: 20. -n is a short flag for --limit. Additional flags: --sort {created,updated}, --branch TEXT (filter by git branch), --cwd [PATH] (filter by working directory; bare flag uses current directory), -v/--verbose (show all columns including branch, created time, and initial prompt), -r/--relative (relative timestamps) |
dcode threads delete ID | Delete a session. Supports --dry-run |
dcode mcp login NAME [--mcp-config PATH] | Run the OAuth login flow for an MCP server marked auth: "oauth". See MCP tools |
dcode mcp config | Show MCP config discovery paths |
dcode config show | Show every config option’s effective value and the source it resolves from. See Inspect configuration |
dcode config list | List all available config options with their type, default, and where each can be set (alias: ls) |
dcode config get KEY | Show the effective value and source for one option (e.g. interpreter.memory_limit_mb) |
dcode config path | Show config file locations and whether each exists |
dcode auth list | List known providers and where each credential resolves from |
dcode auth status <provider> | Show the credential source for one provider |
dcode auth set <provider> | Store a provider credential from stdin or --from-env |
dcode auth remove <provider> | Remove a stored provider credential |
dcode auth path | Show the credential store path |
--json for machine-readable output. See command-line options for more information.
Destructive commands (agents reset, skills delete, threads delete) support --dry-run to preview what would happen without making changes. In JSON mode, --dry-run returns the same envelope with a dry_run: true field.
See also
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.