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 skills add bonnard-data/bonnard-cli --skill bonnard-metabase-migrategit clone --depth 1 https://github.com/bonnard-data/bonnard-cliWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bonnard-data/bonnard-cli/bonnard-metabase-migrate)<a href="https://agentmods.dev/skills/bonnard-data/bonnard-cli/bonnard-metabase-migrate"><img src="https://agentmods.dev/badge/skills/bonnard-data/bonnard-cli/bonnard-metabase-migrate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bonnard-data/bonnard-cli/bonnard-metabase-migrate"><img src="https://agentmods.dev/badge/skills/bonnard-data/bonnard-cli/bonnard-metabase-migrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.02301 |
| Opus 5.5 | $0.00022 | $0.00920 |
| Sonnet 5.5 | $0.00011 | $0.00460 |
| Haiku 4.5 | $0.00006 | $0.00230 |
Grade A, and why
bonnard-metabase-migrate 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 1mo 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate from Metabase to Bonnard
This skill guides you through analyzing an existing Metabase instance and building a semantic layer that replicates its most important metrics. Walk through each phase in order, confirming progress before moving on.
Phase 1: Connect to Metabase
Set up a connection to the Metabase instance:
bon metabase connect
This prompts for the Metabase URL and API key. The API key should be created in Metabase under Admin > Settings > Authentication > API Keys. An admin-level key gives the richest analysis (permissions, schema access).
Phase 2: Analyze the Instance
Generate an intelligence report that maps the entire Metabase instance:
bon metabase analyze
This writes a report to .bon/metabase-analysis.md. Read it carefully — it
drives every decision in the remaining phases.
How to interpret each section
| Report Section | What It Tells You | Action |
|---|---|---|
| Most Referenced Tables | Tables used most in SQL queries | Create cubes for these first — they are the core of the data model |
| Top Cards by Activity | Most-viewed questions/models | analytical cards (GROUP BY + aggregation) map to measures; lookup cards indicate key filter dimensions; display cards can be skipped |
| Common Filter Variables | Template vars ({{var}}) used across 3+ cards |
These must be dimensions on relevant cubes |
| Foreign Key Relationships | FK links between tables | Define joins between cubes using these relationships |
| Collection Structure | How users organize content by business area | Map each top-level collection to a view (one view per business domain) |
| Dashboard Parameters | Shared filters across dashboards | The most important shared dimensions — ensure they exist on relevant cubes |
| Table Inventory | Field counts and classification per table | Field classification (dims/measures/time) guides each cube definition; tables with 0 refs can be deprioritized |
| Schema Access | Which schemas non-admin groups can query | Focus on user-facing schemas — skip admin-only/staging schemas |
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.
- 1mo ago First seen · 278 lines · 55 tokens per session scan A c45f9e27c030
bonnard-metabase-migrate is a skill published in the GitHub repository bonnard-data/bonnard-cli (50 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 2,301 once invoked, about $0.0002 per session on Opus 5.5. 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
skills
The catalog agent is the knowledge hub of the Data Workers swarm. It crawls, indexes, and serves metadata about every data asset across an organization's stack — tables, views, models, pipelines, dashboards, and metrics. It provides natural-language search, column-level lineage, quality scoring, and automated…
incident-rca
Walk a data incident from symptom to root cause: correlate the anomaly, trace the failing upstream job, and produce a root-cause narrative with the evidence chain.
quality-audit
Run a full data-quality audit on a table or pipeline: quality score, rule checks, anomalies with context, and concrete fixes ranked by impact.
trace-lineage
Trace end-to-end lineage for any table or column across catalogs. Answers 'where does this data come from and what breaks if it changes' with a source-to-consumer chain.
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.