bonnard-get-started

A step-by-step guide for creating a first Bonnard semantic layer after `bon init`. A semantic layer gives business data understandable names, relationships, and metrics for people and AI agents.

In plain words
What is it for?
Use it to connect a demo dataset or supported warehouse, then continue building and deploying the data model. Supported sources include PostgreSQL, Redshift, Snowflake, BigQuery, Databricks, and DuckDB.
Why use it?
It provides a starting path when the project has been initialized but is not yet connected to usable data.

Skill for Claude CodeCodex

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 skills/bonnard-data/bonnard-cli/bonnard-get-started
Any agent
npx skills add bonnard-data/bonnard-cli --skill bonnard-get-started
Clone the repo
git clone --depth 1 https://github.com/bonnard-data/bonnard-cli

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,239 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 $0.00045 $0.02239
Opus 5 $0.00023 $0.01120
Sonnet 5 $0.00009 $0.00448
Haiku 4.5 $0.00005 $0.00224

Measured yesterday against content hash 0c30458bf711, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bonnard-get-started 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 yesterday.

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.

src/templates/claude/skills/bonnard-get-started/SKILL.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Get Started with Bonnard

This skill guides you through building and deploying a semantic layer. The user has already run bon init.

IMPORTANT — pacing: Complete ONE phase at a time. Before starting a phase, briefly explain what it does and why. After completing it, show the user what happened and ask if they're ready to move on. Do NOT run through all phases in one go.

Phase 1: Connect a Data Source

Ask the user if they have a warehouse to connect, or want to try a demo dataset first:

# Option A: Use demo data (no warehouse needed)
bon datasource add --demo

# Option B: Import from dbt (if they use it)
bon datasource add --from-dbt

# Option C: Add manually, non-interactive (preferred for agents)
bon datasource add --name my_warehouse --type postgres \
  --host db.example.com --port 5432 --database mydb --schema public \
  --user myuser --password mypassword

# Option D: Add manually, interactive (in user's terminal)
bon datasource add

Supported types: postgres, redshift, snowflake, bigquery, databricks, duckdb.

The demo option adds a read-only Contoso retail dataset with tables like fact_sales, dim_product, dim_store, and dim_customer.

The connection will be tested automatically during bon deploy.

Phase 2: Explore the Data

Before creating cubes, understand what tables and columns are available in your warehouse.

Important: bon query is for querying the deployed semantic layer — it does NOT access your database directly. Use your warehouse's native tools to explore tables.

Options for exploring your data:

  • Use your database CLI (e.g., psql for Postgres/Redshift, snowsql for Snowflake, bq for BigQuery) to list tables and columns
  • Check your dbt docs or existing documentation for table schemas
  • Ask the user for table names and column details if you don't have direct database access
  • For the demo dataset, the tables are: contoso.fact_sales, contoso.dim_product, contoso.dim_store, contoso.dim_customer

Read the full file on GitHub · 253 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. yesterday First seen · 253 lines · 45 tokens per session scan A 0c30458bf711

Subscribe to this mod's changes

bonnard-get-started is a skill published in the GitHub repository bonnard-data/bonnard-cli (50 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 2,239 once invoked, about $0.0002 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 2026-08-30.