# baz.studio — complete API / CLI reference

Generated from the baz CLI v0.8.14. The CLI is the API.


---

---
title: "baz.studio API"
description: "The baz CLI is the Bazaar API — programmatic motion-graphics video generation from your terminal, scripts, and agents."
---

Bazaar turns `brand + skill + context + goal` into rendered motion-graphics videos. There is no separate REST surface to learn: **the `baz` CLI is the API**. Everything the product can do — projects, prompting the autonomous agent, scene-level code edits, media generation, voiceovers, exports — is exposed as a command, with JSON output for programmatic use.

## Install

```bash
npm install -g bazaar.it
```

## Authenticate

```bash
baz auth login
baz auth status
```

## Quickstart

```bash
# Create a project and generate a video with the autonomous agent
baz project create "Product launch teaser"
baz prompt "30s launch teaser for our analytics dashboard, dark theme, bold typography"

# Check progress and export
baz status
baz export
```

## Agent mode

Set `BAZ_AGENT=1` to make every command emit compact JSON — built for scripts, CI, and AI agents:

```bash
BAZ_AGENT=1 baz scenes list
baz prompt --stream-json --events-only "Add a pricing scene"
```

For machine-readable capability discovery, use `baz capabilities --json`.

## Reference

The [CLI reference](/docs/cli) documents every command with options, defaults, and examples. It is generated directly from the CLI's own help system, so it always matches the published version.

For LLMs and agents: [/llms.txt](/llms.txt) is an index of these docs, and [/llms-full.txt](/llms-full.txt) contains the complete reference in one file.


---

---
title: "CLI Reference"
description: "Complete reference for the baz CLI v0.8.14. The CLI is the Bazaar API."
---

The `baz` CLI is the programmatic interface to Bazaar — everything the agent and Studio can do is exposed as a command. Install it with:

```bash
npm install -g bazaar.it
```

This reference is generated from the CLI itself (v0.8.14), so it always matches the published behavior. Set `BAZ_AGENT=1` to get JSON output suited for agents and scripts.

## Global options

| Option | Description |
| --- | --- |
| `-v, --version` | Show version |
| `-i, --interactive` | Start interactive REPL mode |
| `--json` | Output as JSON |
| `--compact` | Compact JSON output (no whitespace, saves tokens) |
| `--verbose` | Show detailed output |
| `--config <path>` | Custom config file path |
| `--api-url <url>` | Override API URL |
| `--project-id <id>` | Override active project |
| `--no-suggestions` | Suppress next-step suggestions |

## Commands

| Command | Description |
| --- | --- |
| [`baz auth`](/docs/cli/auth) | Manage authentication |
| [`baz project`](/docs/cli/project) | Manage projects |
| [`baz prompt`](/docs/cli/prompt) | Send a prompt to the autonomous agent |
| [`baz scenes`](/docs/cli/scenes) | Manage scenes in active project |
| [`baz export`](/docs/cli/export) | Export video from active project |
| [`baz media`](/docs/cli/media) | Manage media files in your project |
| [`baz logs`](/docs/cli/logs) | Query recent project/runtime logs |
| [`baz status`](/docs/cli/status) | Show project overview and timeline |
| [`baz review`](/docs/cli/review) | Get current project state for external agent evaluation |
| [`baz context`](/docs/cli/context) | Manage project context (goals, requirements, references) |
| [`baz capabilities`](/docs/cli/capabilities) | Describe CLI capabilities and protocol support |
| [`baz loop`](/docs/cli/loop) | Iterate prompt → review in a basic OODA loop |
| [`baz state`](/docs/cli/state) | Get a machine-friendly snapshot of current project state |
| [`baz verify`](/docs/cli/verify) | Verify current project against criteria |
| [`baz mcp`](/docs/cli/mcp) | Expose MCP-style tool manifest for agent integrations |
| [`baz template`](/docs/cli/template) | Browse and apply templates |
| [`baz share`](/docs/cli/share) | Create and manage share links for projects |
| [`baz model`](/docs/cli/model) | View and configure AI models for generation |
| [`baz preview`](/docs/cli/preview) | Render a single frame to PNG — visual feedback for agents |
| [`baz balance`](/docs/cli/balance) | Show account balance, spending, and pricing guide |
| [`baz blitz`](/docs/cli/blitz) | Manage Blitz setup, queue, and content drops |
| [`baz brand`](/docs/cli/brand) | Manage reusable brand profiles |
| [`baz calibration`](/docs/cli/calibration) | Create, launch, inspect, and review persisted calibration runs |
| [`baz skills`](/docs/cli/skills) | Manage Claude Code / Codex skills for Baz |
| [`baz skill`](/docs/cli/skill) | Manage Baz-native reusable skills |
| [`baz resource`](/docs/cli/resource) | Compile external resources into Bazaar video context and run them through the existing generator |
| [`baz studio`](/docs/cli/studio) | CLI-first Studio workflows for brand evidence, runs, and claim pages |


---

---
title: "baz auth"
description: "Manage authentication"
---

```bash
baz auth [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz auth login

Configure API key for authentication

```bash
baz auth login [options] [api-key]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz auth register

Create a new account and store an API key

```bash
baz auth register [options]
```

| Option | Description |
| --- | --- |
| `--email <email>` | Email for the new account |
| `--name <name>` | Optional display name |
| `-h, --help` | display help for command |

## baz auth status

Show current authentication status

```bash
baz auth status [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz auth logout

Clear stored credentials

```bash
baz auth logout [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |


---

---
title: "baz project"
description: "Manage projects"
---

```bash
baz project [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz project create

Create a new project

```bash
baz project create [options]
```

| Option | Description |
| --- | --- |
| `--name <name>` | Project name |
| `--description <text>` | Project description |
| `--format <format>` | Video format: landscape, portrait, square Default: `landscape`. |
| `--no-activate` | Don't set as active project |
| `-h, --help` | display help for command |

## baz project list

List all projects

```bash
baz project list [options]
```

| Option | Description |
| --- | --- |
| `--limit <n>` | Number of projects to show Default: `20`. |
| `--all` | Show all projects (no limit) |
| `-h, --help` | display help for command |

## baz project use

Set active project

```bash
baz project use [options] <id>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz project current

Show active project

```bash
baz project current [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz project format

Change project format by duplicating to a new project with target format

```bash
baz project format [options] <format>
```

| Option | Description |
| --- | --- |
| `--source <id>` | Source project ID (defaults to active project) |
| `--no-activate` | Don't set duplicated project as active |
| `-h, --help` | display help for command |

## baz project duplicate

Duplicate a project (optionally changing format)

```bash
baz project duplicate [options] [id]
```

| Option | Description |
| --- | --- |
| `--name <name>` | Rename the duplicated project |
| `--format <format>` | Target format: landscape, portrait, square |
| `--no-activate` | Don't set duplicated project as active |
| `-h, --help` | display help for command |

## baz project settings

View or change project settings (format, dimensions)

```bash
baz project settings [options]
```

| Option | Description |
| --- | --- |
| `--aspect <ratio>` | Set aspect ratio: 16:9, 9:16, 1:1 |
| `--format <format>` | Set format: landscape, portrait, square |
| `-h, --help` | display help for command |

## baz project validate

Validate project timeline structure

```bash
baz project validate [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz project delete

Delete a project

```bash
baz project delete [options] <id>
```

| Option | Description |
| --- | --- |
| `--force` | Skip confirmation |
| `-h, --help` | display help for command |


---

---
title: "baz prompt"
description: "Send a prompt to the autonomous agent"
---

```bash
baz prompt [options] [text]
```

| Option | Description |
| --- | --- |
| `--mode <mode>` | Generation mode: agent (default), agent-max, multi-scene Default: `agent`. |
| `--max` | Shorthand for --mode agent-max |
| `--project <id>` | Alias for global --project-id |
| `--file <path>` | Read prompt from file |
| `--image <path>` | Attach an image file (can be used multiple times) |
| `--url <url>` | Attach a URL for the agent to analyze (can be used multiple times) |
| `--no-stream` | Disable streaming output |
| `--verbose` | Show agent's full response text |
| `--stream-json` | Output events as newline-delimited JSON (for bots like Maya) |
| `--events-only` | With --stream-json, only emit structured events (skip text/thinking tokens) |
| `--spar` | Spar planning mode: brainstorming only, no composition mutations |
| `--plan` | Deprecated alias for --spar |
| `--requirements <list>` | Deterministic requirements to verify against (duration, scenes, format) |
| `--save-context` | Save provided URL/image references to reusable project context |
| `--context-label <label>` | Label for saved context entries (default: reference) Default: `reference`. |
| `--budget <dollars>` | Max budget per run in USD (default: server default) |
| `--model <model>` | Agent model alias or full ID: fast, normal, max, gpt-5.5-low, gpt-5.5-high, gpt-5.5 |
| `--export` | Automatically export the project after successful generation |
| `--export-quality <quality>` | Export quality when using --export: low, medium, high Default: `high`. |
| `--export-format <format>` | Export format when using --export: mp4, webm, gif Default: `mp4`. |
| `--export-timeout <seconds>` | Fail if auto-export takes longer than this Default: `600`. |
| `-h, --help` | display help for command |


---

---
title: "baz scenes"
description: "Manage scenes in active project"
---

```bash
baz scenes [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz scenes list

List all scenes in active project

```bash
baz scenes list [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz scenes code

Show TSX code for a scene

```bash
baz scenes code [options] [scene-id]
```

| Option | Description |
| --- | --- |
| `--all` | Show code for all scenes |
| `--output <path>` | Write to file instead of stdout |
| `-h, --help` | display help for command |

## baz scenes delete

Delete a scene

```bash
baz scenes delete [options] <scene-id>
```

| Option | Description |
| --- | --- |
| `--force` | Skip confirmation |
| `-h, --help` | display help for command |

## baz scenes rename

Rename a scene

```bash
baz scenes rename [options] <scene-id>
```

| Option | Description |
| --- | --- |
| `--name <name>` | New scene name |
| `-h, --help` | display help for command |

## baz scenes move

Move a scene to a different track/position on the timeline

```bash
baz scenes move [options] <scene-id>
```

| Option | Description |
| --- | --- |
| `--track <number>` | Target track number |
| `--start <frame>` | Target start frame |
| `--duration <frames>` | New duration in frames |
| `-h, --help` | display help for command |

## baz scenes reorder

Reorder scenes by passing scene IDs in playback order

```bash
baz scenes reorder [options]
```

| Option | Description |
| --- | --- |
| `--ids <ids>` | Comma-separated scene IDs (full or unique prefix) in new playback order |
| `--ids-file <path>` | Read IDs from file (JSON array or one ID per line) |
| `-h, --help` | display help for command |

## baz scenes create

Create a new scene from TSX code (no AI tokens spent)

```bash
baz scenes create [options]
```

| Option | Description |
| --- | --- |
| `--name <name>` | Scene name |
| `--file <path>` | Read TSX code from file |
| `--code <code>` | Provide TSX code inline |
| `--duration <frames>` | Duration in frames (default: 150) Default: `150`. |
| `--track <number>` | Track number (default: 0) Default: `0`. |
| `--start <frame>` | Start frame (default: 0) Default: `0`. |
| `-h, --help` | display help for command |

## baz scenes set-code

Replace scene TSX code (for agent-driven edits)

```bash
baz scenes set-code [options] <scene-id>
```

| Option | Description |
| --- | --- |
| `--file <path>` | Read new code from file |
| `--code <code>` | Provide new code inline |
| `--overwrite-duration` | Also update scene duration from code |
| `-h, --help` | display help for command |

## baz scenes positions

Preview or apply timeline position updates from JSON

```bash
baz scenes positions [options]
```

| Option | Description |
| --- | --- |
| `--updates-file <path>` | Path to JSON array (or &#123;"updates":[...]&#125;) |
| `--updates-json <json>` | Inline JSON array (or &#123;"updates":[...]&#125;) |
| `--apply` | Persist changes (default: dry-run preview) |
| `-h, --help` | display help for command |

## baz scenes history

Show edit history for a scene

```bash
baz scenes history [options] <scene-id>
```

| Option | Description |
| --- | --- |
| `--limit <n>` | Number of iterations to show Default: `10`. |
| `-h, --help` | display help for command |

## baz scenes restore

Restore scene code from a specific history iteration

```bash
baz scenes restore [options] <scene-id>
```

| Option | Description |
| --- | --- |
| `--iteration <iteration-id>` | Iteration ID to restore (full or prefix) |
| `--force` | Skip confirmation |
| `-h, --help` | display help for command |

## baz scenes undo

Restore the latest restorable scene code iteration

```bash
baz scenes undo [options] <scene-id>
```

| Option | Description |
| --- | --- |
| `--force` | Skip confirmation |
| `-h, --help` | display help for command |


---

---
title: "baz export"
description: "Export video from active project"
---

```bash
baz export [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz export start

Start a video export/render

```bash
baz export start [options]
```

| Option | Description |
| --- | --- |
| `--quality <quality>` | Video quality: low, medium, high Default: `high`. |
| `--format <format>` | Output format: mp4, webm, gif Default: `mp4`. |
| `--thumbnail-frame <number>` | Frame number to use for the generated poster/thumbnail still |
| `--wait` | Block until export completes (agent-friendly) |
| `--timeout <seconds>` | Fail if export takes longer than this (requires --wait) Default: `600`. |
| `-h, --help` | display help for command |

## baz export status

Check export status

```bash
baz export status [options] <renderId>
```

| Option | Description |
| --- | --- |
| `--wait` | Wait for completion |
| `--timeout <seconds>` | Fail if export takes longer than this (requires --wait) Default: `600`. |
| `-h, --help` | display help for command |

## baz export list

List recent exports

```bash
baz export list [options]
```

| Option | Description |
| --- | --- |
| `--limit <n>` | Number of exports to show Default: `10`. |
| `-h, --help` | display help for command |


---

---
title: "baz media"
description: "Manage media files in your project"
---

```bash
baz media [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz media upload

Upload an image, video, or audio file to the media library

```bash
baz media upload [options] <file>
```

| Option | Description |
| --- | --- |
| `--name <name>` | Custom name for the uploaded file |
| `-h, --help` | display help for command |

## baz media list

List uploaded media files for the active project

```bash
baz media list [options]
```

| Option | Description |
| --- | --- |
| `--type <type>` | Filter by type: image, video, audio, logo |
| `--limit <n>` | Max items to show Default: `50`. |
| `-h, --help` | display help for command |

## baz media compress

Generate lightweight preview renditions for all project video media (run after batch-uploading clips)

```bash
baz media compress [options]
```

| Option | Description |
| --- | --- |
| `--info` | Report master vs preview sizes without compressing anything |
| `--fix-masters` | Losslessly remux non-faststart masters in place first (fixes slow Lambda frame extraction on first export) |
| `-h, --help` | display help for command |

## baz media transcribe-voiceover

Transcribe an uploaded audio asset with Whisper word timestamps and persist voiceover alignment metadata

```bash
baz media transcribe-voiceover [options] <assetId>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz media tts

Generate a voiceover audio asset directly in Bazaar

Alias: `voiceover`

```bash
baz media tts [options] <text>
```

| Option | Description |
| --- | --- |
| `--provider <provider>` | TTS provider: gemini, minimax, or elevenlabs Default: `gemini`. |
| `--voice-id <voiceId>` | Provider voice ID. Gemini accepts Gemini voice names; ElevenLabs requires a connected voice |
| `--voice-style <style>` | Gemini voice direction, e.g. warm documentary narrator, calm British presenter |
| `--emotion <emotion>` | MiniMax emotion hint, e.g. happy, sad, calm, excited |
| `--speed <speed>` | MiniMax speed: 0.5-2.0 |
| `--pitch <pitch>` | MiniMax pitch: -12 to 12 |
| `--raw` | Use text exactly as the spoken script; disables MiniMax AI voice interpretation |
| `-h, --help` | display help for command |

```text
What it does:
  Generates one voiceover/audio asset directly in Bazaar and attaches it to the active project.
  Use this when you want reusable narration audio without going through the chat agent.

Pricing estimate:
  --provider gemini      $0.08 per started minute  (Gemini 3.1 Flash TTS Preview)
  --provider minimax     $0.06 per started 1k characters  (Minimax Speech)
  --provider elevenlabs  $0.44 per estimated minute, or $0.00/min with connected BYOK

Provider notes:
  gemini is the default and uses Google Gemini TTS voices through Bazaar.
  gemini supports --voice-id plus --voice-style for delivery direction.
  If --voice-style is omitted, Bazaar reuses the project's stored voice style or derives one from project context.
  Supported Gemini voice IDs include Kore (default), Zephyr, Puck, Charon, Aoede, Leda, Orus, Fenrir.
  minimax supports emotion, speed, pitch, and optional AI voice interpretation.
  elevenlabs requires a connected ElevenLabs key/default voice or a --voice-id.

Examples:
  baz media tts --provider gemini "Welcome to the listing. This home opens with warm natural light."
  baz media tts --provider gemini --voice-id Zephyr --voice-style "warm, calm, real-estate documentary narrator" "A calm editorial narration for a finance explainer."
  baz media tts --provider minimax --emotion happy --speed 1.05 "Three reasons this product launch matters."

Live pricing:
  baz balance --pricing
```

## baz media imagegen2

Generate an Image Gen 2 image directly in Bazaar (verbatim prompt, no agent rewriting)

```bash
baz media imagegen2 [options] <prompt>
```

| Option | Description |
| --- | --- |
| `--provider <provider>` | Image provider: openai, nanobanana, or flux Default: `openai`. |
| `--aspect-ratio <ratio>` | Aspect ratio: 1:1, 16:9, 9:16, 4:3, 3:4, 21:9 Default: `1:1`. |
| `--format <fmt>` | Output format: jpg, png, webp Default: `jpg`. |
| `--input-image <path>` | Repeatable reference image input. Limits: openai=1, nanobanana=3, flux=8 |
| `-h, --help` | display help for command |

```text
What it does:
  Generates or edits one image directly through Bazaar Image Gen 2.
  The prompt is sent verbatim; the autonomous video agent does not rewrite it.
  The output is uploaded to Bazaar media and returned as a reusable URL/asset id.

Inputs:
  prompt                 Required text prompt.
  --input-image <path>   Repeatable reference image input. Limits: openai=1, nanobanana=3, flux=8.
  --aspect-ratio         Output shape. Common: 1:1, 16:9, 9:16, 4:3, 3:4, 21:9.
  --format               Output image format: jpg, png, or webp.

Pricing estimate:
  --provider openai      $0.10 per image  (OpenAI GPT Image 2)
  --provider nanobanana  $0.08 per image  (NanoBanana)
  --provider flux        $0.08 per image  (FLUX 2 Pro)
  If --provider is omitted, the CLI uses openai/Image Gen 2.

Provider notes:
  openai accepts at most one --input-image.
  flux is best for clean text-to-image generation.
  nanobanana is available as a separate provider/fallback.

Examples:
  baz media imagegen2 --aspect-ratio 16:9 "Luxury real estate dusk exterior, cinematic"
  baz media imagegen2 --input-image ./kitchen.jpg "Make this kitchen brighter and editorial"
  baz media imagegen2 --provider flux --format webp "Minimal SaaS dashboard hero image"

Live pricing:
  baz balance --pricing
```

## baz media seedance2

Generate a Seedance 2.0 video directly in Bazaar

```bash
baz media seedance2 [options] <prompt>
```

| Option | Description |
| --- | --- |
| `--model <model>` | Seedance model ID |
| `--aspect-ratio <ratio>` | Aspect ratio: 16:9, 9:16, 1:1 Default: `16:9`. |
| `--resolution <resolution>` | Resolution: 480p, 720p, 1080p Default: `720p`. |
| `--duration <seconds>` | Duration in seconds: 2-12 Default: `5`. |
| `--image <path>` | First-frame image for image-to-video |
| `--last-frame <path>` | Last-frame image for frame interpolation |
| `-h, --help` | display help for command |

```text
What it does:
  Generates a short Seedance 2.0 AI video directly through Bazaar media generation.
  The prompt is sent verbatim; the autonomous video agent does not rewrite it.
  The output is uploaded to Bazaar media and returned as a reusable URL/asset id.

Models:
  doubao-seedance-2-0-260128          Seedance 2.0 on Volcengine Ark
  doubao-seedance-2-0-fast-260128     Seedance 2.0 Fast on Volcengine Ark
  dreamina-seedance-2-0-260128        Seedance 2.0 on BytePlus ModelArk
  dreamina-seedance-2-0-fast-260128   Seedance 2.0 Fast on BytePlus ModelArk
  If --model is omitted, Bazaar uses the server-configured default model.

Inputs:
  prompt                 Required text prompt.
  --image <path>         Optional first-frame image for image-to-video.
  --last-frame <path>    Optional ending frame for interpolation when supported.
  --aspect-ratio         Output video shape: 16:9, 9:16, or 1:1.
  --resolution           Output resolution: 480p, 720p, or 1080p.
  --duration             Output duration in seconds: 2-12.

Pricing estimate:
  Seedance 2 is billed from actual Ark token usage returned by the completed task.
  Bazaar price uses a 50% gross margin over the provider token cost.
  Standard, no video input: 480p/720p $0.0140/1K tokens, 1080p $0.0154/1K tokens
  Standard, video input:    480p/720p $0.0086/1K tokens, 1080p $0.0094/1K tokens
  Fast, no video input:     480p/720p $0.0112/1K tokens
  Fast, video input:        480p/720p $0.0066/1K tokens
  Seedance 2.0 Fast does not support 1080p output; use standard Seedance 2.0 for 1080p.

Reference frames:
  --image uploads a first-frame image for image-to-video.
  --last-frame uploads an ending frame for interpolation when supported by the model.
  Image reference frames do not count as Ark video input for pricing; the CLI normally uses the no-video-input token rate.

Examples:
  baz media seedance2 --resolution 720p --duration 5 "Slow dolly through a sunlit real estate living room"
  baz media seedance2 --aspect-ratio 9:16 --duration 6 --image ./exterior.jpg "Subtle cinematic push-in at golden hour"
  baz media seedance2 --model dreamina-seedance-2-0-260128 --resolution 720p "Polished product teaser"
  baz media seedance2 --model doubao-seedance-2-0-fast-260128 --resolution 480p "Fast social teaser for a property listing"

Live pricing:
  baz balance --pricing
```


---

---
title: "baz logs"
description: "Query recent project/runtime logs"
---

```bash
baz logs [options]
```

| Option | Description |
| --- | --- |
| `--errors` | Show only errors |
| `--search <text>` | Search for text in log messages |
| `--path <path>` | Filter by API path (e.g., /api/generate-stream) |
| `--since <time>` | Time range: 5m, 1h, 24h, 7d (default: 1h) Default: `1h`. |
| `--limit <n>` | Maximum number of logs to show (default: 50) Default: `50`. |
| `--project` | Filter logs by current project ID |
| `-h, --help` | display help for command |


---

---
title: "baz status"
description: "Show project overview and timeline"
---

```bash
baz status [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |


---

---
title: "baz review"
description: "Get current project state for external agent evaluation"
---

```bash
baz review [options]
```

| Option | Description |
| --- | --- |
| `--include-code` | Include full TSX code for each scene (default: true) |
| `--no-code` | Exclude TSX code (smaller payload) |
| `--summary` | Compact summary (no TSX code or full context) |
| `-h, --help` | display help for command |


---

---
title: "baz context"
description: "Manage project context (goals, requirements, references)"
---

```bash
baz context [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz context add

Add context to the current project

```bash
baz context add [options] [content]
```

| Option | Description |
| --- | --- |
| `--label <label>` | Label for this context (e.g., "goal", "requirement", "brand") |
| `--file <path>` | Upload a file as context (PDF, image, video) |
| `--type <type>` | Content type: text, url, file, image, video |
| `-h, --help` | display help for command |

## baz context list

List all context for the current project

```bash
baz context list [options]
```

| Option | Description |
| --- | --- |
| `--label <label>` | Filter by label |
| `-h, --help` | display help for command |

## baz context remove

Remove a specific context entry

```bash
baz context remove [options] <id>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz context clear

Clear all context for the current project

```bash
baz context clear [options]
```

| Option | Description |
| --- | --- |
| `--label <label>` | Only clear context with this label |
| `-h, --help` | display help for command |

## baz context generate

Generate a reusable skill from the current project

```bash
baz context generate [options]
```

| Option | Description |
| --- | --- |
| `--prompt <text>` | Focus extraction on specific aspects (e.g. "the warm palette and animation style") |
| `--output <path>` | Write the generated preset markdown to a file |
| `--activate` | Save the generated markdown as the project's latest preset context |
| `--apply` | Alias for --activate |
| `-h, --help` | display help for command |

## baz context show

Show all context for the current project (alias for list)

```bash
baz context show [options]
```

| Option | Description |
| --- | --- |
| `--label <label>` | Filter by label |
| `-h, --help` | display help for command |


---

---
title: "baz capabilities"
description: "Describe CLI capabilities and protocol support"
---

```bash
baz capabilities [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |


---

---
title: "baz loop"
description: "Iterate prompt → review in a basic OODA loop"
---

```bash
baz loop [options] [text]
```

| Option | Description |
| --- | --- |
| `--mode <mode>` | Generation mode: agent (default), agent-max, multi-scene Default: `agent`. |
| `--max` | Shorthand for --mode agent-max |
| `--max-iterations <n>` | Maximum iterations (default: 3) Default: `3`. |
| `--time-limit <time>` | Total wall-clock time limit (e.g., 45s, 2m, 1h); aborts in-flight generation when exceeded |
| `--budget <time>` | [deprecated] Alias for --time-limit. Note: baz prompt --budget is dollars; this is time |
| `--stop-on-fail` | Stop the loop on generation failure |
| `--requirements <list>` | Deterministic requirements to verify against (duration, scenes, format) |
| `--file <path>` | Read prompt from file |
| `--image <path>` | Attach an image file (can be used multiple times) |
| `--url <url>` | Attach a URL for the agent to analyze (can be used multiple times) |
| `--save-context` | Save provided URL/image references to reusable project context |
| `--context-label <label>` | Label for saved context entries (default: reference) Default: `reference`. |
| `--no-stream` | Disable streaming output |
| `--stream-json` | Output events as newline-delimited JSON |
| `-h, --help` | display help for command |


---

---
title: "baz state"
description: "Get a machine-friendly snapshot of current project state"
---

```bash
baz state [options]
```

| Option | Description |
| --- | --- |
| `--include-code` | Include scene TSX code in scene payload |
| `--include-messages` | Include recent project messages |
| `-h, --help` | display help for command |


---

---
title: "baz verify"
description: "Verify current project against criteria"
---

```bash
baz verify [options]
```

| Option | Description |
| --- | --- |
| `--criteria <list>` | Comma-separated criteria to verify |
| `--query <text>` | Single verification query |
| `--scene <id>` | Scope verification to one scene ID (supports prefix) |
| `-h, --help` | display help for command |


---

---
title: "baz mcp"
description: "Expose MCP-style tool manifest for agent integrations"
---

```bash
baz mcp [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz mcp tools

List MCP tool names

```bash
baz mcp tools [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |


---

---
title: "baz template"
description: "Browse and apply templates"
---

```bash
baz template [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz template list

List available templates

```bash
baz template list [options]
```

| Option | Description |
| --- | --- |
| `--catalog <catalog>` | Catalog scope: curated or all Default: `curated`. |
| `--include-multiscene` | Include multi-scene templates |
| `--category <category>` | Filter by category |
| `--format <format>` | Filter by format: landscape, portrait, square |
| `--search <query>` | Search templates by name/description |
| `--limit <n>` | Max results Default: `20`. |
| `-h, --help` | display help for command |

## baz template recommend

Recommend templates for a prompt

```bash
baz template recommend [options] <prompt>
```

| Option | Description |
| --- | --- |
| `--catalog <catalog>` | Catalog scope: curated or all Default: `curated`. |
| `--include-multiscene` | Include multi-scene templates |
| `--limit <n>` | Max recommendations Default: `5`. |
| `-h, --help` | display help for command |

## baz template show

Show template details

```bash
baz template show [options] <template-id>
```

| Option | Description |
| --- | --- |
| `--code` | Include TSX template code |
| `--output <path>` | Write TSX code to file (implies --code) |
| `-h, --help` | display help for command |

## baz template apply

Add template scene(s) to a project

```bash
baz template apply [options] <template-id>
```

| Option | Description |
| --- | --- |
| `--project-id <id>` | Override active project |
| `-h, --help` | display help for command |

## baz template publish

**Enterprise / service accounts.** Used by managed content pipelines; requires a service account on a [Business plan](/pricing).

Publish a project as a community template (admin beta)

```bash
baz template publish [options]
```

| Option | Description |
| --- | --- |
| `--name <name>` | Template name |
| `--project-id <id>` | Override active project |
| `--scene-ids <ids>` | Comma-separated scene UUIDs (defaults to all active project scenes) |
| `--description <description>` | Template description |
| `--category <category>` | Template category |
| `--tags <tags>` | Comma-separated tags |
| `--formats <formats>` | Comma-separated formats: landscape, portrait, square |
| `--preview-url <url>` | Preview video URL |
| `--var <key=value>` | Declare editable variable (repeatable) |
| `--dry-run` | Validate and score publish payload without writing |
| `-h, --help` | display help for command |


---

---
title: "baz share"
description: "Create and manage share links for projects"
---

```bash
baz share [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz share create

Create a share link for the active project

```bash
baz share create [options]
```

| Option | Description |
| --- | --- |
| `--title <title>` | Custom title for the shared page |
| `--description <desc>` | Description for the shared page |
| `-h, --help` | display help for command |

## baz share list

List all your shared projects

```bash
baz share list [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz share delete

Delete a share link

```bash
baz share delete [options] <share-id>
```

| Option | Description |
| --- | --- |
| `--force` | Skip confirmation |
| `-h, --help` | display help for command |


---

---
title: "baz model"
description: "View and configure AI models for generation"
---

```bash
baz model [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz model show

Show current model configuration

```bash
baz model show [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz model list

Show available models with pricing

```bash
baz model list [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz model set

Set orchestrator, codegen, and optional visual-review model by number

```bash
baz model set [options] <orchestrator> [codegen] [visualReviewer]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz model reset

Reset to default models

```bash
baz model reset [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |


---

---
title: "baz preview"
description: "Render a single frame to PNG — visual feedback for agents"
---

```bash
baz preview [options]
```

| Option | Description |
| --- | --- |
| `--frame <number>` | Frame number to render (default: middle of video) |
| `--frames <list>` | Comma-separated frame numbers (e.g., 0,150,500) |
| `--output <path>` | Write PNG to local file |
| `-h, --help` | display help for command |


---

---
title: "baz balance"
description: "Show account balance, spending, and pricing guide"
---

```bash
baz balance [options] [command]
```

| Option | Description |
| --- | --- |
| `--pricing` | Show operation pricing guide |
| `-h, --help` | display help for command |

## baz balance topup

Create a Stripe checkout link to add balance (minimum $5)

```bash
baz balance topup [options] <amount>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |


---

---
title: "baz blitz"
description: "Manage Blitz setup, queue, and content drops"
---

```bash
baz blitz [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz blitz setup

Create or update Blitz brand setup from structured input

```bash
baz blitz setup [options]
```

| Option | Description |
| --- | --- |
| `--stdin-json` | Read JSON input from stdin |
| `--file <path>` | Read JSON input from a file |
| `-h, --help` | display help for command |

## baz blitz schedule

Create or update Blitz cadence and budget

```bash
baz blitz schedule [options]
```

| Option | Description |
| --- | --- |
| `--stdin-json` | Read JSON input from stdin |
| `--file <path>` | Read JSON input from a file |
| `-h, --help` | display help for command |

## baz blitz drop

Create a manual Blitz content request

```bash
baz blitz drop [options]
```

| Option | Description |
| --- | --- |
| `--url <url>` | Create a URL content drop |
| `--text <text>` | Create a text or idea content drop |
| `--stdin-json` | Read JSON input from stdin |
| `-h, --help` | display help for command |

## baz blitz queue

Inspect the Blitz queue

```bash
baz blitz queue [options]
```

| Option | Description |
| --- | --- |
| `--status <status>` | Filter by status |
| `--limit <number>` | Number of items to return Default: `20`. |
| `-h, --help` | display help for command |

## baz blitz status

Show Blitz onboarding, budget, and queue summary

```bash
baz blitz status [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz blitz claim

**Enterprise / service accounts.** Used by managed content pipelines; requires a service account on a [Business plan](/pricing).

Claim the next due Blitz request (admin/service-account)

```bash
baz blitz claim [options]
```

| Option | Description |
| --- | --- |
| `--due-before <iso>` | Only claim requests due before this ISO timestamp |
| `-h, --help` | display help for command |

## baz blitz request

Show a single Blitz request with variants

```bash
baz blitz request [options] <requestId>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz blitz save-variant

**Enterprise / service accounts.** Used by managed content pipelines; requires a service account on a [Business plan](/pricing).

Create or update a Blitz variant record (admin/service-account)

```bash
baz blitz save-variant [options]
```

| Option | Description |
| --- | --- |
| `--stdin-json` | Read JSON input from stdin |
| `--file <path>` | Read JSON input from a file |
| `-h, --help` | display help for command |

## baz blitz mark-ready

**Enterprise / service accounts.** Used by managed content pipelines; requires a service account on a [Business plan](/pricing).

Mark a Blitz request ready for review (admin/service-account)

```bash
baz blitz mark-ready [options]
```

| Option | Description |
| --- | --- |
| `--stdin-json` | Read JSON input from stdin |
| `--file <path>` | Read JSON input from a file |
| `-h, --help` | display help for command |

## baz blitz mark-failed

**Enterprise / service accounts.** Used by managed content pipelines; requires a service account on a [Business plan](/pricing).

Mark a Blitz request failed or requeue it (admin/service-account)

```bash
baz blitz mark-failed [options]
```

| Option | Description |
| --- | --- |
| `--stdin-json` | Read JSON input from stdin |
| `--file <path>` | Read JSON input from a file |
| `-h, --help` | display help for command |

## baz blitz approve

Approve a Blitz variant for a request

```bash
baz blitz approve [options]
```

| Option | Description |
| --- | --- |
| `--request-id <id>` | Request ID |
| `--variant-id <id>` | Variant ID |
| `-h, --help` | display help for command |

## baz blitz prepare-project

**Enterprise / service accounts.** Used by managed content pipelines; requires a service account on a [Business plan](/pricing).

Create or reuse a Baz workspace project for a Blitz request (admin/service-account)

```bash
baz blitz prepare-project [options]
```

| Option | Description |
| --- | --- |
| `--request-id <id>` | Request ID |
| `-h, --help` | display help for command |

## baz blitz execute-request

**Enterprise / service accounts.** Used by managed content pipelines; requires a service account on a [Business plan](/pricing).

Prepare a Blitz request project and generate through Baz chat (admin/service-account)

```bash
baz blitz execute-request [options]
```

| Option | Description |
| --- | --- |
| `--request-id <id>` | Request ID |
| `--variant-label <label>` | Variant label to save Default: `A`. |
| `--mode <mode>` | Generation mode: agent, agent-max, or multi-scene Default: `agent-max`. |
| `-h, --help` | display help for command |

## baz blitz work-once

**Enterprise / service accounts.** Used by managed content pipelines; requires a service account on a [Business plan](/pricing).

Claim the next due Blitz request and execute it through Baz chat (admin/service-account)

```bash
baz blitz work-once [options]
```

| Option | Description |
| --- | --- |
| `--due-before <iso>` | Only claim requests due before this ISO timestamp |
| `--variant-label <label>` | Variant label to save Default: `A`. |
| `--mode <mode>` | Generation mode: agent, agent-max, or multi-scene Default: `agent-max`. |
| `-h, --help` | display help for command |


---

---
title: "baz brand"
description: "Manage reusable brand profiles"
---

```bash
baz brand [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz brand setup

Create or update your saved brand profile from structured input

```bash
baz brand setup [options]
```

| Option | Description |
| --- | --- |
| `--stdin-json` | Read JSON input from stdin |
| `--file <path>` | Read JSON input from a file |
| `-h, --help` | display help for command |

## baz brand status

Show whether you have a saved brand profile

```bash
baz brand status [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz brand list

List your saved profile brand and current project brand artifacts

```bash
baz brand list [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz brand activate

Make a saved project brand the active profile brand

```bash
baz brand activate [options] <brand-id>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |


---

---
title: "baz calibration"
description: "Create, launch, inspect, and review persisted calibration runs"
---

```bash
baz calibration [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz calibration create

Create a persisted calibration run from JSON matrix input

```bash
baz calibration create [options]
```

| Option | Description |
| --- | --- |
| `--file <path>` | Read calibration JSON from a file |
| `--stdin-json` | Read calibration JSON from stdin |
| `--launch` | Launch all created variants immediately |
| `--mode <mode>` | Generation mode for --launch (agent or agent-max) Default: `agent-max`. |
| `--concurrency <number>` | Parallel variant launches Default: `1`. |
| `--budget <usd>` | Per-variant budget cap in USD |
| `--export` | Automatically export the project after successful generation |
| `--export-quality <quality>` | Export quality when using --export: low, medium, high Default: `high`. |
| `--export-format <format>` | Export format when using --export: mp4, webm, gif Default: `mp4`. |
| `--export-timeout <seconds>` | Fail if auto-export takes longer than this Default: `600`. |
| `-h, --help` | display help for command |

## baz calibration launch

Launch pending variants for an existing calibration run

```bash
baz calibration launch [options] <runId>
```

| Option | Description |
| --- | --- |
| `--mode <mode>` | Generation mode (agent or agent-max) Default: `agent-max`. |
| `--concurrency <number>` | Parallel variant launches Default: `1`. |
| `--budget <usd>` | Per-variant budget cap in USD |
| `--all` | Launch all variants, including already completed ones |
| `--only <keys>` | Comma-separated variant keys to launch |
| `--export` | Automatically export the project after successful generation |
| `--export-quality <quality>` | Export quality when using --export: low, medium, high Default: `high`. |
| `--export-format <format>` | Export format when using --export: mp4, webm, gif Default: `mp4`. |
| `--export-timeout <seconds>` | Fail if auto-export takes longer than this Default: `600`. |
| `-h, --help` | display help for command |

## baz calibration list

List recent calibration runs

```bash
baz calibration list [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz calibration show

Show a calibration run with variant status, scores, and project links

```bash
baz calibration show [options] <runId>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz calibration review

Save operator review feedback for a calibration variant

```bash
baz calibration review [options] <variantId>
```

| Option | Description |
| --- | --- |
| `--score <number>` | Overall score from 0 to 10 |
| `--clear-score` | Clear the saved score |
| `--notes <text>` | Review notes |
| `--notes-file <path>` | Read review notes from a file |
| `--winner` | Mark this variant as the winner for the run |
| `--clear-winner` | Clear winner state for this variant |
| `--failure-tags <tags>` | Comma-separated failure tags |
| `--clear-failure-tags` | Clear saved failure tags |
| `-h, --help` | display help for command |


---

---
title: "baz skills"
description: "Manage Claude Code / Codex skills for Baz"
---

```bash
baz skills [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz skills install

Install a Baz skill into .claude/skills/ for Claude Code

```bash
baz skills install [options] <name>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz skills list

List available Baz skills

```bash
baz skills list [options]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |


---

---
title: "baz skill"
description: "Manage Baz-native reusable skills"
---

```bash
baz skill [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz skill list

List available Baz-native skills

```bash
baz skill list [options]
```

| Option | Description |
| --- | --- |
| `--limit <n>` | Max skills to fetch Default: `60`. |
| `-h, --help` | display help for command |

## baz skill show

Show a saved skill

```bash
baz skill show [options] <skill-ref>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz skill patterns

List pattern ids in a saved skill

```bash
baz skill patterns [options] <skill-ref>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz skill deps

List linked references inside a saved skill

```bash
baz skill deps [options] <skill-ref>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz skill init

Create a starter local skill markdown file

```bash
baz skill init [options] <slug>
```

| Option | Description |
| --- | --- |
| `--output <path>` | Path to write the starter skill markdown |
| `-h, --help` | display help for command |

## baz skill draft

Draft a skill from the current project

```bash
baz skill draft [options]
```

| Option | Description |
| --- | --- |
| `--output <path>` | Path to write the drafted markdown |
| `--project <id>` | Override project id |
| `--project-id <id>` | Alias for --project |
| `--prompt <text>` | Focus extraction on specific aspects |
| `-h, --help` | display help for command |

## baz skill draft-project

Draft a project-backed skill and write an agent review packet

```bash
baz skill draft-project [options]
```

| Option | Description |
| --- | --- |
| `--project <id>` | Source project id |
| `--project-id <id>` | Alias for --project |
| `--output <path>` | Path to write the drafted markdown |
| `--prompt <text>` | Focus extraction on specific aspects |
| `--review-output <path>` | Path to write the senior-agent review packet |
| `--validation-output <path>` | Path to write machine-readable validation JSON |
| `--allow-blockers` | Exit 0 even when mechanical project-skill blockers remain |
| `--allow-missing-narration` | Allow draft generation when source audio exists but accepted script/narration evidence is missing |
| `-h, --help` | display help for command |

## baz skill review-project

Validate an edited project-backed skill and write an agent review packet

```bash
baz skill review-project [options] <path>
```

| Option | Description |
| --- | --- |
| `--project <id>` | Source project id |
| `--project-id <id>` | Alias for --project |
| `--review-output <path>` | Path to write the senior-agent review packet |
| `--validation-output <path>` | Path to write machine-readable validation JSON |
| `--allow-blockers` | Exit 0 even when mechanical project-skill blockers remain |
| `-h, --help` | display help for command |

## baz skill compare-project

Compare two project-backed skill drafts against the same source project

```bash
baz skill compare-project [options] <left-path> <right-path>
```

| Option | Description |
| --- | --- |
| `--project <id>` | Source project id |
| `--left-label <label>` | Label for the first skill Default: `left`. |
| `--right-label <label>` | Label for the second skill Default: `right`. |
| `--comparison-output <path>` | Path to write the comparison markdown |
| `-h, --help` | display help for command |

## baz skill pull

Write a saved skill to a local file for editing

```bash
baz skill pull [options] <skill-ref>
```

| Option | Description |
| --- | --- |
| `--output <path>` | Path to write the markdown |
| `-h, --help` | display help for command |

## baz skill validate

Validate local skill markdown

```bash
baz skill validate [options] <path>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz skill save

Save local skill markdown into the current project skill library

```bash
baz skill save [options] <path>
```

| Option | Description |
| --- | --- |
| `--project <id>` | Override project id |
| `--project-id <id>` | Alias for --project |
| `--skill <skill-ref>` | Overwrite an existing saved skill by slug or context ID |
| `--publish` | Publish the saved skill into the public /create skill catalog (admin only) |
| `--catalog-slug <slug>` | Override the /create catalog slug when publishing |
| `--catalog-title <title>` | Override the /create catalog title when publishing |
| `--promise <text>` | Public promise copy for the /create skill card |
| `--description <text>` | Public description copy for the /create skill card |
| `--preview-url <url>` | Preview video URL for the /create skill card |
| `--poster-url <url>` | Preview poster URL for the /create skill card |
| `--format <formats>` | Supported format(s): portrait, landscape, square, or comma-separated |
| `--duration <seconds>` | Default duration in seconds for guided create |
| `--sort-order <n>` | Sort order in the /create catalog |
| `--voiceover <yes\|no\|maybe>` | Default voiceover preference for guided create |
| `-h, --help` | display help for command |

## baz skill activate

Activate a saved skill as the project preset

```bash
baz skill activate [options] <skill-ref>
```

| Option | Description |
| --- | --- |
| `--project <id>` | Override project id |
| `--project-id <id>` | Alias for --project |
| `-h, --help` | display help for command |

## baz skill link

Edit local skill markdown bindings

```bash
baz skill link [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

### baz skill link add

Add a linked pattern binding to a local skill markdown file

```bash
baz skill link add [options] <path>
```

| Option | Description |
| --- | --- |
| `--pattern <skill#pattern>` | Linked pattern reference, e.g. mobile-ui#fit-to-stage |
| `--beat <beat>` | Beat key to bind |
| `--transition <from:to>` | Transition pair to bind, e.g. proof-1:proof-2 |
| `-h, --help` | display help for command |


---

---
title: "baz resource"
description: "Compile external resources into Bazaar video context and run them through the existing generator"
---

```bash
baz resource [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz resource compile

Compile a URL or file into a resource-video spec

```bash
baz resource compile [options] <source>
```

| Option | Description |
| --- | --- |
| `--archetype <type>` | auto, one-page-infographic, article-to-editorial-data-story, research-report, product-announcement Default: `auto`. |
| `--format <format>` | auto, landscape, portrait, square Default: `auto`. |
| `--brand <ref>` | Brand reference to record in the spec |
| `--skill <ref>` | Skill reference to record in the spec |
| `--gold-brief` | Emit panel-map, layout-shell, scene-briefs, voiceover-script, timing-plan, verification criteria, and quality-bar |
| `--output <path>` | Write spec JSON to a file |
| `-h, --help` | display help for command |

## baz resource run

Create a normal Bazaar project from a resource-video spec and optionally generate

```bash
baz resource run [options] <spec>
```

| Option | Description |
| --- | --- |
| `--project-name <name>` | Project name |
| `--project-id <id>` | Use an existing project instead of creating a new one |
| `--brand-file <path>` | Add this brand.md as brand + brand-preset context |
| `--brand-profile` | Use saved profile brand.md as brand + brand-preset context |
| `--skill <ref>` | Activate an existing saved skill by slug or context ID |
| `--skill-file <path>` | Save and activate this local skill markdown |
| `--run` | Generate the video after context setup |
| `--generate` | Alias for --run |
| `--prompt <text>` | Override the generation prompt used with --run |
| `--mode <mode>` | Generation mode: agent or agent-max Default: `agent`. |
| `--budget <dollars>` | Max budget per run in USD |
| `--allow-low-balance` | Start generation even if balance is below the estimated budget for a complete resource video |
| `--model <model>` | Agent model alias or full ID |
| `-h, --help` | display help for command |


---

---
title: "baz studio"
description: "CLI-first Studio workflows for brand evidence, runs, and claim pages"
---

```bash
baz studio [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz studio brand

Manage Studio brand records

```bash
baz studio brand [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

### baz studio brand ensure

Create or update a reusable Studio brand record

```bash
baz studio brand ensure [options]
```

| Option | Description |
| --- | --- |
| `--url <url>` | Brand website URL or domain |
| `--name <name>` | Display name |
| `--brand-markdown <markdown>` | Optional authored brand.md content |
| `--visibility <visibility>` | private, unlisted, or public Default: `unlisted`. |
| `--review-status <status>` | automated, approved, or rejected Default: `approved`. |
| `-h, --help` | display help for command |

## baz studio evidence

Manage typed brand evidence and claims

```bash
baz studio evidence [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

### baz studio evidence list

List typed claims for a brand

```bash
baz studio evidence list [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--claim-type <type>` | Filter by claim type |
| `--status <status>` | Filter by status |
| `--limit <n>` | Max claims to return Default: `100`. |
| `-h, --help` | display help for command |

### baz studio evidence add

Add one or more manual typed claims to a brand

```bash
baz studio evidence add [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--file <path>` | JSON array or object with a claims array |
| `--claim <text>` | Claim text for single-claim entry |
| `--claim-type <type>` | Claim type for single-claim entry |
| `--value <value>` | Numeric/string value for stat or pricing claims |
| `--unit <unit>` | Unit for the value |
| `--attribution <attribution>` | self_claim, third_party, or verified Default: `self_claim`. |
| `--source-url <url>` | Source URL |
| `--source-type <type>` | Source type Default: `manual`. |
| `--quote <quote>` | Exact source quote |
| `--confidence <confidence>` | low, medium, or high Default: `high`. |
| `--status <status>` | draft, approved, or rejected Default: `approved`. |
| `-h, --help` | display help for command |

### baz studio evidence review

Update claim review status

```bash
baz studio evidence review [options] <claim-id>
```

| Option | Description |
| --- | --- |
| `--status <status>` | draft, approved, or rejected |
| `--confidence <confidence>` | low, medium, or high |
| `-h, --help` | display help for command |

### baz studio evidence resolve

Resolve a skill input contract against typed brand evidence

```bash
baz studio evidence resolve [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--skill <skill>` | Official skill slug or id Default: `charts-data`. |
| `--format <format>` | landscape, portrait, or square |
| `--duration <seconds>` | Requested duration in seconds |
| `--max-claims <n>` | Maximum approved claims to inspect Default: `10`. |
| `-h, --help` | display help for command |

### baz studio evidence materialize-finance

Dry-run or execute finance evidence seed materialization into Studio claims and chart assets

```bash
baz studio evidence materialize-finance [options]
```

| Option | Description |
| --- | --- |
| `--seed-jsonl <path>` | Studio evidence seed JSONL |
| `--source-jsonl <path>` | Finance source fixture JSONL for sourceId cross-checking |
| `--run-story-jsonl <path>` | run_story_v0 draft JSONL for exact-quote coverage checking |
| `--source-id <id>` | Only materialize one sourceId |
| `--execute` | Write Studio rows for --source-id or all rows when omitted |
| `--create-evidence-packs` | Create completed source_bundle evidence pack snapshots after execute writes |
| `-h, --help` | display help for command |

## baz studio screenshots

Manage typed brand screenshot and image asset purposes

```bash
baz studio screenshots [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

### baz studio screenshots add

Add or adopt a screenshot URL as a typed brand asset

```bash
baz studio screenshots add [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--url <url>` | Screenshot image URL |
| `--purpose <purpose>` | Screenshot purpose |
| `--source-url <url>` | Page URL or source URL represented by the screenshot |
| `--name <name>` | Original/display name for the asset |
| `--viewport <viewport>` | Viewport label, e.g. desktop or mobile |
| `--width <px>` | Image width in pixels |
| `--height <px>` | Image height in pixels |
| `-h, --help` | display help for command |

### baz studio screenshots list

List brand screenshots and typed image assets

```bash
baz studio screenshots list [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--purpose <purpose>` | Filter by screenshot purpose |
| `--no-legacy` | Hide legacy brand_repository.screenshots entries |
| `-h, --help` | display help for command |

### baz studio screenshots update

Set or clear the purpose for a typed brand screenshot asset

```bash
baz studio screenshots update [options] <brand-asset-id>
```

| Option | Description |
| --- | --- |
| `--purpose <purpose>` | home_hero, pricing_table, product_dashboard, customer_logos, case_study_metric, docs_ui, chart_source, or social_proof |
| `--clear-purpose` | Clear the current purpose |
| `-h, --help` | display help for command |

## baz studio ingest

Create browser-use/browser-harness ingestion jobs for reusable evidence packs

```bash
baz studio ingest [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

### baz studio ingest start

Create a queued browser ingestion job and evidence-pack contract

```bash
baz studio ingest start [options]
```

| Option | Description |
| --- | --- |
| `--url <url>` | Brand website URL or domain |
| `--name <name>` | Display name |
| `--backend <backend>` | manual, source_bundle, browser_use, browser_harness, or playwright Default: `browser_use`. |
| `-h, --help` | display help for command |

## baz studio evidence-pack

Persist and inspect reusable brand evidence packs

```bash
baz studio evidence-pack [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

### baz studio evidence-pack create

Snapshot the current typed brand claims/assets into a durable evidence pack

```bash
baz studio evidence-pack create [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--backend <backend>` | manual, source_bundle, browser_use, browser_harness, or playwright Default: `browser_use`. |
| `--status <status>` | queued, running, completed, failed, or needs_review Default: `completed`. |
| `--notes <notes>` | Optional operator notes |
| `-h, --help` | display help for command |

### baz studio evidence-pack list

List persisted evidence packs for a brand

```bash
baz studio evidence-pack list [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--status <status>` | Filter by status |
| `--limit <n>` | Max packs to return Default: `20`. |
| `-h, --help` | display help for command |

### baz studio evidence-pack import

Persist a browser-use evidence-pack JSON file and optionally create draft claims

```bash
baz studio evidence-pack import [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--file <path>` | Evidence pack JSON file |
| `--backend <backend>` | manual, source_bundle, browser_use, browser_harness, or playwright Default: `browser_use`. |
| `--status <status>` | queued, running, completed, failed, or needs_review Default: `needs_review`. |
| `--no-draft-claims` | Do not create draft brand_claim rows from evidencePack.claims |
| `-h, --help` | display help for command |

### baz studio evidence-pack import-resource

Convert a baz resource compile spec into approved claims and a Studio evidence pack

```bash
baz studio evidence-pack import-resource [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--file <path>` | resource-video.v1 JSON file from baz resource compile |
| `--backend <backend>` | manual, source_bundle, browser_use, browser_harness, or playwright Default: `source_bundle`. |
| `--status <status>` | queued, running, completed, failed, or needs_review Default: `completed`. |
| `--claim-status <status>` | draft, approved, or rejected Default: `approved`. |
| `--max-claims <n>` | Maximum claims to materialize from the resource spec Default: `12`. |
| `--notes <notes>` | Optional operator notes |
| `-h, --help` | display help for command |

## baz studio plan

Create and inspect durable Studio production plans

```bash
baz studio plan [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

### baz studio plan create

Create a durable Studio plan and queued source-backed runs

```bash
baz studio plan create [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--title <title>` | Plan title |
| `--skills <skills>` | Comma-separated official skill slugs or ids Default: `charts-data`. |
| `--count <n>` | Total number of planned runs to create Default: `5`. |
| `--formats <formats>` | Comma-separated formats: portrait, landscape, square Default: `portrait`. |
| `--evidence-pack-id <id>` | Evidence pack id to pin in sourceInputSnapshot |
| `--duration <seconds>` | Requested duration in seconds |
| `--max-claims <n>` | Maximum approved claims to inspect per resolver pass Default: `10`. |
| `--allow-missing` | Create the plan even if resolver reports missing evidence |
| `--planner-profile <profile>` | Planner profile label; stored literally for audit/config resolution |
| `--status <status>` | planning, queued, executing, reviewed, published, or failed Default: `queued`. |
| `--run-status <status>` | Initial brand_run status for generated runs Default: `queued`. |
| `-h, --help` | display help for command |

### baz studio plan import

Import a frozen story plan (run_story_v0 JSONL) into Studio

```bash
baz studio plan import [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--jsonl <path>` | Path to a run_story_v0 JSONL file |
| `--title <title>` | Plan title |
| `--planner-profile <profile>` | Planner profile label (e.g. deepseek-v4-flash); stored literally for audit |
| `--source-label <label>` | Free-form provenance label written into planMetadata.sourceLabel (no path leakage) |
| `--on-unresolved <mode>` | fail \| warn \| drop (default fail) Default: `fail`. |
| `--status <status>` | Plan status: planning, queued, executing, reviewed, published, failed Default: `queued`. |
| `--run-status <status>` | Initial brand_run status for generated runs Default: `queued`. |
| `--evidence-pack-id <id>` | Evidence pack id to pin in planMetadata |
| `--limit <n>` | Cap rows imported (testing aid) |
| `--brand-filter <domain>` | Only import rows whose brandDomain matches the given string (case-insensitive) |
| `--allow-mismatched-profile` | Continue when JSONL row models do not match --planner-profile (off by default) |
| `-h, --help` | display help for command |

### baz studio plan list

List durable Studio plans for a brand

```bash
baz studio plan list [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--status <status>` | Filter by plan status |
| `--limit <n>` | Max plans to return Default: `20`. |
| `-h, --help` | display help for command |

### baz studio plan inspect

Inspect a Studio plan and its linked runs

```bash
baz studio plan inspect [options] <plan-id>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

## baz studio runs

Create and inspect persisted Studio brand_run rows

```bash
baz studio runs [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

### baz studio runs create

Create one Studio run and freeze the resolver binding plan into brand_run

```bash
baz studio runs create [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--skill <skill>` | Official skill slug or id Default: `charts-data`. |
| `--brief <brief>` | Run brief |
| `--evidence-pack-id <id>` | Evidence pack id to pin in sourceInputSnapshot |
| `--plan-id <id>` | Studio brand_plan id to link |
| `--format <format>` | landscape, portrait, or square |
| `--duration <seconds>` | Requested duration in seconds |
| `--max-claims <n>` | Maximum approved claims to inspect Default: `10`. |
| `--allow-missing` | Create the run even if resolver reports missing evidence |
| `--status <status>` | Initial brand_run status Default: `queued`. |
| `-h, --help` | display help for command |

### baz studio runs batch

Create queued Studio runs for one brand across skills and briefs

```bash
baz studio runs batch [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--skills <skills>` | Comma-separated official skill slugs or ids Default: `charts-data`. |
| `--brief <brief>` | One brief. Can be repeated by shell aliases via --briefs-file for now |
| `--briefs-file <path>` | JSON array/object or newline-delimited brief file |
| `--count <n>` | Number of generic briefs to create when no brief is supplied Default: `1`. |
| `--evidence-pack-id <id>` | Evidence pack id to pin in sourceInputSnapshot |
| `--format <format>` | landscape, portrait, or square |
| `--duration <seconds>` | Requested duration in seconds |
| `--max-claims <n>` | Maximum approved claims to inspect Default: `10`. |
| `--allow-missing` | Create runs even if resolver reports missing evidence |
| `--status <status>` | Initial brand_run status Default: `queued`. |
| `-h, --help` | display help for command |

### baz studio runs list

List Studio runs for a brand

```bash
baz studio runs list [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--status <status>` | Filter by brand_run status |
| `--plan-id <id>` | Filter by Studio brand_plan id |
| `--limit <n>` | Max runs to return Default: `20`. |
| `-h, --help` | display help for command |

### baz studio runs inspect

Inspect a Studio run including resolved bindings, source input, and output snapshot

```bash
baz studio runs inspect [options] <run-id>
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

### baz studio runs review

Review a generated Studio run with deterministic gates, optional LLM judgment, and optional rendered-frame vision review

```bash
baz studio runs review [options] <run-id>
```

| Option | Description |
| --- | --- |
| `--model <model>` | Reviewer model id from models.config.ts Default: `deepseek-v4-flash`. |
| `--worker <worker>` | Reviewer worker id for audit metadata |
| `--no-llm` | Skip the LLM pass and run deterministic checks only |
| `--visual` | Render representative frames and include a vision model review |
| `--visual-reviewer-model <model>` | Visual reviewer model id from models.config.ts |
| `--frames-per-scene <n>` | Frames to render per scene for --visual Default: `3`. |
| `--max-visual-frames <n>` | Maximum visual review frames to render/send Default: `24`. |
| `--expected-status <status>` | Require the run to currently have this status |
| `-h, --help` | display help for command |

### baz studio runs claim

Atomically claim one queued Studio run for a worker

```bash
baz studio runs claim [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--worker <worker>` | Worker id, e.g. claude-worker-1 |
| `--skill <skill>` | Filter by official skill slug or id |
| `--scan-limit <n>` | Max queued candidates to scan Default: `10`. |
| `-h, --help` | display help for command |

### baz studio runs work

Claim, execute, and optionally review queued Studio runs in a worker loop

```bash
baz studio runs work [options]
```

| Option | Description |
| --- | --- |
| `--brand <brand>` | Brand id, URL, domain, or short domain prefix |
| `--worker <worker>` | Worker id, e.g. studio-worker-1 |
| `--skill <skill>` | Filter by official skill slug or id |
| `--limit <n>` | Maximum runs this process should claim before exiting Default: `10`. |
| `--until-empty` | Ignore --limit and keep claiming until no queued run is available |
| `--scan-limit <n>` | Max queued candidates to scan per claim attempt Default: `10`. |
| `--mode <mode>` | Generation mode: agent, agent-max, or multi-scene Default: `agent`. |
| `--model <model>` | Agent/orchestrator model alias or full model id |
| `--codegen-model <model>` | Codegen model alias or full model id |
| `--voiceover-provider <provider>` | TTS provider for voiceover-led Studio runs: gemini or elevenlabs |
| `--voiceover-voice-id <voiceId>` | Voice id to pass to media.generate_voiceover for voiceover-led Studio runs |
| `--complete` | Mark successful execution completed instead of needs_review |
| `--review` | Run Studio review immediately after successful execution |
| `--review-model <model>` | Reviewer model id from models.config.ts Default: `deepseek-v4-flash`. |
| `--visual-review` | When reviewing, render representative frames and include a vision model review |
| `--visual-reviewer-model <model>` | Visual reviewer model id from models.config.ts |
| `--frames-per-scene <n>` | Frames to render per scene for --visual-review Default: `3`. |
| `--max-visual-frames <n>` | Maximum visual review frames to render/send Default: `24`. |
| `--no-llm` | When --review is set, skip the reviewer LLM pass |
| `--stop-on-error` | Stop the loop after the first failed execution/review |
| `-h, --help` | display help for command |

### baz studio runs execute

Execute one claimed Studio run by creating a Bazaar project from its frozen resolver snapshot

```bash
baz studio runs execute [options] <run-id>
```

| Option | Description |
| --- | --- |
| `--worker <worker>` | Worker id for claim/complete/fail metadata Default: `studio-cli-worker`. |
| `--claim-if-queued` | Atomically claim this exact run if it is still queued |
| `--mode <mode>` | Generation mode: agent, agent-max, or multi-scene Default: `agent`. |
| `--model <model>` | Agent/orchestrator model alias or full model id |
| `--codegen-model <model>` | Codegen model alias or full model id |
| `--voiceover-provider <provider>` | TTS provider for voiceover-led Studio runs: gemini or elevenlabs |
| `--voiceover-voice-id <voiceId>` | Voice id to pass to media.generate_voiceover for voiceover-led Studio runs |
| `--complete` | Mark successful execution completed instead of needs_review |
| `-h, --help` | display help for command |

### baz studio runs complete

Mark a running Studio run completed (or needs_review) with output metadata

```bash
baz studio runs complete [options] <run-id>
```

| Option | Description |
| --- | --- |
| `--worker <worker>` | Worker id, mirrored into outputSnapshot.completion.worker |
| `--project-id <id>` | Bazaar project id created by the worker |
| `--export-id <id>` | Lambda export/render id, if any |
| `--scene-ids <ids>` | Comma-separated list of generated scene ids |
| `--review-status <status>` | pending, needs_review, approved, or rejected Default: `pending`. |
| `--notes <notes>` | Free-form completion notes for the reviewer |
| `--needs-review` | Mark final status as needs_review instead of completed |
| `--output-json <path>` | JSON file with extra outputSnapshot patch fields |
| `--expected-status <status>` | Required prior status Default: `running`. |
| `-h, --help` | display help for command |

### baz studio runs fail

Mark a running Studio run failed with a recorded reason

```bash
baz studio runs fail [options] <run-id>
```

| Option | Description |
| --- | --- |
| `--reason <reason>` | Failure reason for outputSnapshot.failure.reason |
| `--worker <worker>` | Worker id, mirrored into outputSnapshot.failure.worker |
| `--output-json <path>` | JSON file with extra outputSnapshot patch fields |
| `--expected-status <status>` | Required prior status Default: `running`. |
| `-h, --help` | display help for command |

## baz studio batch

Run Studio import, execution, and review pipelines from planner artifacts

```bash
baz studio batch [options] [command]
```

| Option | Description |
| --- | --- |
| `-h, --help` | display help for command |

### baz studio batch run

Batch import run_story_v0 rows, execute the resulting Studio runs, and optionally review them

```bash
baz studio batch run [options]
```

| Option | Description |
| --- | --- |
| `--jsonl <path>` | Path to run_story_v0 JSONL |
| `--brands <brands>` | Comma-separated brand domains/refs to run from the JSONL |
| `--import` | Import matching JSONL rows into Studio plans/runs |
| `--execute` | Execute imported runs after import |
| `--review` | Review successfully executed runs |
| `--visual` | When reviewing, render representative frames and include visual review |
| `--planner-profile <profile>` | Planner profile label; hard-warned against JSONL model values |
| `--allow-mismatched-profile` | Continue when --planner-profile is not present in selected JSONL rows |
| `--source-label <label>` | Free-form provenance label for imported plans |
| `--title-prefix <title>` | Prefix for imported plan titles Default: `Studio batch`. |
| `--on-unresolved <mode>` | fail \| warn \| drop (default fail) Default: `fail`. |
| `--status <status>` | Plan status for imported plans Default: `queued`. |
| `--run-status <status>` | Initial run status for imported runs Default: `queued`. |
| `--evidence-pack-id <id>` | Evidence pack id to pin in imported plan metadata |
| `--limit <n>` | Global cap on selected JSONL rows |
| `--limit-per-brand <n>` | Cap selected JSONL rows per brand |
| `--concurrency <n>` | Concurrent execution/review workers Default: `1`. |
| `--worker <worker>` | Worker id prefix for execution/review metadata Default: `studio-batch`. |
| `--mode <mode>` | Generation mode: agent, agent-max, or multi-scene Default: `agent`. |
| `--model <model>` | Agent/orchestrator model alias or full model id |
| `--codegen-model <model>` | Codegen model alias or full model id |
| `--voiceover-provider <provider>` | TTS provider for voiceover-led Studio runs: gemini or elevenlabs |
| `--voiceover-voice-id <voiceId>` | Voice id to pass to media.generate_voiceover for voiceover-led Studio runs |
| `--review-model <model>` | Reviewer model id from models.config.ts Default: `deepseek-v4-flash`. |
| `--visual-reviewer-model <model>` | Visual reviewer model id from models.config.ts |
| `--frames-per-scene <n>` | Frames to render per scene for --visual Default: `1`. |
| `--max-visual-frames <n>` | Maximum visual review frames to render/send Default: `10`. |
| `--no-llm` | When reviewing, skip the text reviewer LLM pass |
| `--stop-on <mode>` | never \| import-fail \| execute-fail \| review-fail \| hard-fail \| any-fail Default: `never`. |
| `--budget-usd <amount>` | Operator budget label for the batch report; not a hard billing limiter yet |
| `--report-jsonl <path>` | Write one JSONL report row per selected story/run |
| `-h, --help` | display help for command |