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 metabase/agent-skills --skill v1git clone --depth 1 https://github.com/metabase/agent-skillsWrote 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/metabase/agent-skills/v1)<a href="https://agentmods.dev/skills/metabase/agent-skills/v1"><img src="https://agentmods.dev/badge/skills/metabase/agent-skills/v1/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/metabase/agent-skills/v1"><img src="https://agentmods.dev/badge/skills/metabase/agent-skills/v1.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 | $0.00139 | $0.00616 |
| Opus 5.5 | $0.00056 | $0.00246 |
| Sonnet 5.5 | $0.00028 | $0.00123 |
| Haiku 4.5 | $0.00014 | $0.00062 |
Grade A, and why
metabase-data-apps 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 6d 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.
What it actually says
Metabase data apps
This skill is split into parts, one per task. Each part is a guide in its own folder, together with the files only that task uses. Paths in this skill are relative to <skill-dir>, the directory holding this SKILL.md.
Read only the parts the task needs
Every guide is long, and its rules apply only to its own task. Pick the parts from the user's request, read those guides, and leave the others unread.
| The task | Read |
|---|---|
| Create, scaffold, or remove an app; the dev preview and its diagnostics feed; syncing an app to Metabase; an app-wide error | setup/setup.md |
| Change an existing app's UI without new data or writes: layout, theme, SDK components, how a chart renders | setup/setup.md, from Source conventions on |
Show Metabase data: tables, metrics, segments, measures, saved questions, filters, charts, the generated metabase.data.ts |
semantic-layer/semantic-layer.md |
| More than one page: routes, links between pages, the current path | routing/routing.md |
| A write: a form, a button that creates, updates, or deletes, running an action | actions/actions.md |
Metabase marks the app Outdated, the user asks to migrate it, or npm run typecheck or npm run build fails after an SDK upgrade |
migrate/migrate.md |
- Don't read
routing/routing.mdunless the app needs more than one page. - Don't read
actions/actions.mdunless the app writes data. - Don't read
migrate/migrate.mdunless the app needs migrating as the table says. An app Metabase doesn't mark Outdated, and that builds, needs no migration. - A task can span parts: a new app that shows a metric needs
setup/setup.md, thensemantic-layer/semantic-layer.md. Read each part when the work reaches it, not all of them up front. - When a guide points to another part or to a file under its own
references/, read it only when you reach that step.
What ships with it
23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- actions/actions.md 16 KB
- migrate/migrate.md 13 KB
- migrate/references/maintainer-checklist.md 4.0 KB
- migrate/references/upgrade-guide-template.md 3.5 KB
- migrate/references/upgrades/README.md 487 B
- routing/routing.md 8.2 KB
- semantic-layer/references/filter-ui-patterns.md 10 KB
- semantic-layer/references/visualization-settings.md 3.4 KB
- semantic-layer/semantic-layer.md 57 KB
- setup/.gitignore 121 B
- setup/setup.md 51 KB
- setup/template/.env.local.example 72 B
- setup/template/.gitignore 36 B
- setup/template/actions/README.md 2.7 KB
- setup/template/LICENSE 1.0 KB
- setup/template/package.json 825 B
- setup/template/queries/README.md 2.8 KB
- setup/template/README.md 995 B
- setup/template/src/App.tsx 260 B
- setup/template/src/index.tsx 446 B
- setup/template/src/theme.ts 454 B runs code
- setup/template/tsconfig.json 679 B
- setup/template/vite.config.ts 116 B runs code
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.
- 6d ago First seen · 31 lines · 139 tokens per session scan A 2e2e5cfd92d7
metabase-data-apps is a skill published in the GitHub repository metabase/agent-skills (50 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 616 once invoked, about $0.0006 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 2026-10-10.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
material-ui-tailwind
Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.
fuzzy-ranking
Rank fuzzy matches with rankItem, filter with RankingInfo.passed, compare saved ranking metadata with compareItems, and configure rankings, thresholds, accessors, min/max bounds, or diacritics. Load for @tanstack/match-sorter-utils itself or fuzzy Table filterMeta wiring.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
git-safety
Git safety rules. INVOKE WHEN: git push, force push, git reset, git clean, destructive git, push force, reset hard. NEVER force push or do destructive git operations.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.