baml-schema

A command for displaying or designing BAML schemas, which define the fields and types expected from an AI extraction task. It represents relationships between types with Mermaid diagrams, a text format for diagrams.

In plain words
What is it for?
Use it to visualize a schema from a file or function, or design new types and complete BAML code for tasks such as extracting meeting notes or invoice data.
Why use it?
It makes existing data structures easier to inspect and helps plan a suitable design before writing extraction code.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/agentic-insights/foundry/baml-schema
Clone the repo
git clone --depth 1 https://github.com/Agentic-Insights/foundry
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 641 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.00641
Opus 5 $0.00006 $0.00320
Sonnet 5 $0.00002 $0.00128
Haiku 4.5 $0.00001 $0.00064

Measured 2d ago against content hash cb6c9a9a6a5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

baml-schema scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/baml/commands/baml-schema.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visualize/Design BAML Schema

Create or visualize BAML schemas with mermaid diagrams.

Modes

Visualize Existing Schema

If $ARGUMENTS is a file path or function name:

  1. Read the schema
  2. Generate mermaid class diagram
  3. Show relationships between types

Design New Schema

If $ARGUMENTS describes a data extraction task:

  1. Analyze requirements
  2. Design appropriate BAML types
  3. Create mermaid visualization
  4. Generate complete BAML code

Visualization Output

For a schema like:

class Invoice {
  vendor Company
  line_items LineItem[]
  total float
}

class Company {
  name string
  address string
}

class LineItem {
  description string
  quantity int
  price float
}

Generate:

classDiagram
    class Invoice {
        +Company vendor
        +LineItem[] line_items
        +float total
    }
    class Company {
        +string name
        +string address
    }
    class LineItem {
        +string description
        +int quantity
        +float price
    }
    Invoice --> Company : vendor
    Invoice --> LineItem : line_items

Design Mode

If $ARGUMENTS describes a task like "extract meeting notes":

  1. Ask clarifying questions (if needed):

    • What fields are required?
    • Are there optional fields?
    • Any validation rules?
  2. Generate schema:

class ActionItem {
  assignee string
  task string
  due_date string?
}

class MeetingNotes {
  title string
  date string
  attendees string[]
  action_items ActionItem[]
}
  1. Generate function:
function ExtractMeetingNotes(transcript: string) -> MeetingNotes {
  client GPT4
  prompt #"
    Extract meeting notes:
    {{ transcript }}
    {{ ctx.output_format }}
  "#
}
  1. Generate test:
test MeetingTest {
  functions [ExtractMeetingNotes]
  args {
    transcript "Meeting on Jan 15..."
  }
}

Arguments

$ARGUMENTS can be:

  • File path: /baml-schema baml_src/invoice.baml
  • Function name: /baml-schema ExtractInvoice
  • Task description: /baml-schema extract receipt data from images
  • Empty: Visualize all schemas in project

Read the full file on GitHub · 138 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 138 lines · 12 tokens per session scan A cb6c9a9a6a5b

Subscribe to this mod's changes

baml-schema is a command published in the GitHub repository Agentic-Insights/foundry (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 641 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.