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.
npx agentmods add skills/bonnard-data/bonnard-cli/bonnard-design-guidenpx skills add bonnard-data/bonnard-cli --skill bonnard-design-guidegit clone --depth 1 https://github.com/bonnard-data/bonnard-cliWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00034 | $0.02141 |
| Opus 5 | $0.00017 | $0.01071 |
| Sonnet 5 | $0.00007 | $0.00428 |
| Haiku 4.5 | $0.00003 | $0.00214 |
Grade A, and why
bonnard-design-guide 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.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Layer Design Guide
This guide covers design decisions that determine whether your semantic layer
works for end users and AI agents. It complements the setup guides
(/bonnard-get-started, /bonnard-metabase-migrate) which cover mechanics.
Read this before building views, or revisit it when agents return wrong answers or users can't find the right metrics.
Principle 1: Start from Questions, Not Tables
The natural instinct is: look at tables, build cubes, expose everything. This produces a semantic layer that mirrors your warehouse schema — technically correct but useless to anyone who doesn't already know the schema.
Instead, start from what people ask:
- Collect the 10-20 most common questions your team asks about data
- For each question, identify which tables/columns are needed to answer it
- Group questions by audience (who asks them)
- Build views that answer those question groups
If you have a BI tool (Metabase, Looker, Tableau), your top dashboards by view count are the best source of real questions. If not, ask each team: "What 3 numbers do you check every week?"
Why this matters: A semantic layer built from questions produces focused, audience-scoped views. One built from tables produces generic views that agents struggle to choose between. Governance policies control which views each user or role can access, so build as many views as your audiences need — but make each one purposeful with clear descriptions.
Principle 2: Views Are for Audiences, Not Tables
A common mistake is creating one view per cube (table). This produces views
like orders_view, users_view, invoices_view — which is just the
warehouse schema with extra steps.
Views should represent how a team thinks about data:
BAD (model-centric): GOOD (audience-centric):
views/ views/
orders_view.yaml (1 cube) management.yaml (revenue + users)
users_view.yaml (1 cube) sales.yaml (opportunities + invoices)
invoices_view.yaml (1 cube) product.yaml (users + funnel + contracts)
opportunities_view.yaml (1 cube) partners.yaml (partners + billing)
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.
- 2d ago First seen · 235 lines · 34 tokens per session scan A 2c3462c19b21
bonnard-design-guide is a skill published in the GitHub repository bonnard-data/bonnard-cli (50 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 2,141 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.
Other skills, from other repositories
metric-definitions
Returns the canonical metric definitions for this project: CVR formula (session vs click), ROAS calculation (Google AOV-based vs Meta platform-native), attribution windows, revenue scopes, funnel integrity rules, and channel attribution normalisation. Use this skill before generating any dashboard or when a metric…
skills
Goal: Ensure all marketing analytics responses are professional, data-driven, and actionable.
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.
notion
Notion API for creating and managing pages, databases, and blocks. Use when the user wants to create a Notion page, query a Notion database, update Notion properties, search Notion, add content to Notion, manage Notion blocks, or interact with Notion data sources and workspaces via the API.
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
connector-standards
Load all OpenMetadata connector development standards into context. Use before building or reviewing connectors to ensure consistent patterns.