> ## Documentation Index > Fetch the complete documentation index at: https://docs.tracks.alpic.ai/llms.txt > Use this file to discover all available pages before exploring further. # tracks runs > Manage runs ## tracks runs create Start a run ```bash theme={null} tracks runs create [flags] ``` | Argument | Type | Required | Description | | - | - | - | - | | `prompt` | `string` | yes | Prompt sent to the agent | | Option | Type | Description | | - | - | - | | `--harness`, `-H` | `choice` | Harness running the agent (choices: claude-code, claude-desktop, codex, codex-app, cursor) | | `--model`, `-m` | `string` | Model used by the harness | | `--file`, `-f` | `file` | Local file uploaded and placed in the sandbox before setup, its path given to the agent with the prompt; repeat for several | | `--repository`, `-r` | `string` | Git repository cloned into the sandbox | | `--env`, `-e` | `string` | Environment variable set in the agent's processes, as KEY=VALUE, or KEY to pass its local value | | `--setup` | `string` | Shell script run in the sandbox after checkout, before the first prompt; from a file: --setup "\$(cat setup.sh)" | | `--teardown` | `string` | Shell script run in the sandbox after the run ends, before the sandbox is destroyed; from a file: --teardown "\$(cat teardown.sh)" | | `--mcp` | `string` | MCP server the agent can use, as NAME=URL, called without credentials, or NAME=CONNECTION\_ID, called as the user who connected it | | `--mcp-header` | `string` | Header added to every request to the MCP server NAME given by URL, typically its API key, as NAME=HEADER: VALUE, such as 'docs=Authorization: Bearer KEY' | | `--browser` | `boolean` | Give the agent a browser, a headless Chromium in its sandbox whose pages can offer it tools through WebMCP. The Codex app and Claude Cowork always use their own browser instead | | `--budget`, `-b` | `number` | Most the run may spend, in US dollars | | `--one-shot` | `boolean` | End the run once its first prompt finishes (default); --no-one-shot waits for follow-ups | | `--idle-timeout` | `integer` | Seconds an idle run waits for a follow-up before it ends | | `--time-limit` | `integer` | Longest the run may last, in seconds, before it is stopped | | `--idempotency-key` | `string` | Retry safely: running again with the same key returns the run already created | | `--label` | `string` | Label attached to the run to find it again, as KEY:VALUE, such as ticket:ENG-42; repeat for several | ## tracks runs list List your runs, most recently started first ```bash theme={null} tracks runs list [flags] ``` | Option | Type | Description | | - | - | - | | `--label` | `string` | Only runs with this label, as KEY:VALUE; repeat to require several | | `--after`, `-a` | `string` | Only runs listed after the run with this id | | `--limit`, `-l` | `integer` | Maximum runs returned | ## tracks runs get Show a run ```bash theme={null} tracks runs get [flags] ``` | Argument | Type | Required | Description | | - | - | - | - | | `id` | `string` | yes | Run id | ## tracks runs send-prompt Send a follow-up prompt to an idle run ```bash theme={null} tracks runs send-prompt [flags] ``` | Argument | Type | Required | Description | | - | - | - | - | | `id` | `string` | yes | Run id | | `text` | `string` | yes | Follow-up prompt sent to the agent | | Option | Type | Description | | - | - | - | | `--model`, `-m` | `string` | Model for this prompt only | ## tracks runs prompts List a run's prompts ```bash theme={null} tracks runs prompts [flags] ``` | Argument | Type | Required | Description | | - | - | - | - | | `id` | `string` | yes | Run id | | Option | Type | Description | | - | - | - | | `--after`, `-a` | `integer` | Only prompts with a greater index | | `--limit`, `-l` | `integer` | Maximum prompts returned | ## tracks runs frames List a run's frames ```bash theme={null} tracks runs frames [flags] ``` | Argument | Type | Required | Description | | - | - | - | - | | `id` | `string` | yes | Run id | | Option | Type | Description | | - | - | - | | `--after`, `-a` | `integer` | Only frames with a greater seq | | `--limit`, `-l` | `integer` | Maximum frames returned | | `--prompt`, `-p` | `integer` | Only frames of this prompt, by index | ## tracks runs events List a run's events ```bash theme={null} tracks runs events [flags] ``` | Argument | Type | Required | Description | | - | - | - | - | | `id` | `string` | yes | Run id | | Option | Type | Description | | - | - | - | | `--after`, `-a` | `integer` | Only events with a greater seq | | `--limit`, `-l` | `integer` | Maximum events returned | | `--prompt`, `-p` | `integer` | Only events of this prompt, by index | ## tracks runs follow Print a run's frames, or its events with --events, as they come, one JSON object per line, until the run ends; exit with code 2 when it ended before its agent finished ```bash theme={null} tracks runs follow [flags] ``` | Argument | Type | Required | Description | | - | - | - | - | | `id` | `string` | yes | Run id | | Option | Type | Description | | - | - | - | | `--after`, `-a` | `integer` | Only frames, or events with --events, with a greater seq | | `--events`, `-e` | `boolean` | Follow the run's events instead of its frames | ## tracks runs usage Show what a run consumed and what it cost ```bash theme={null} tracks runs usage [flags] ``` | Argument | Type | Required | Description | | - | - | - | - | | `id` | `string` | yes | Run id | ## tracks runs end End a run once its current prompt finishes ```bash theme={null} tracks runs end [flags] ``` | Argument | Type | Required | Description | | - | - | - | - | | `id` | `string` | yes | Run id | ## tracks runs cancel Stop a run right away, even mid-prompt ```bash theme={null} tracks runs cancel [flags] ``` | Argument | Type | Required | Description | | - | - | - | - | | `id` | `string` | yes | Run id | This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.