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 metabase-semantic-checkergit 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/metabase-semantic-checker)<a href="https://agentmods.dev/skills/metabase/agent-skills/metabase-semantic-checker"><img src="https://agentmods.dev/badge/skills/metabase/agent-skills/metabase-semantic-checker/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/metabase-semantic-checker"><img src="https://agentmods.dev/badge/skills/metabase/agent-skills/metabase-semantic-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium MCP Rug Pull · line 10 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 41 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 43 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 52 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 54 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 82 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00121 | $0.01488 |
| Opus 5 | $0.00060 | $0.00744 |
| Sonnet 5 | $0.00024 | $0.00298 |
| Haiku 4.5 | $0.00012 | $0.00149 |
Grade A, and why
metabase-semantic-checker 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 11d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metabase semantic checker
The semantic checker validates a tree of Metabase Representation Format YAML files for referential integrity. Schema-level validation (shape of each file, required fields, enum values) is handled separately by npx @metabase/representations validate-schema; the semantic checker runs after schema validation and focuses on cross-file and cross-system consistency.
It compiles every MBQL query down to SQL against the database metadata and checks that each entity reference and each column reference resolves to something that actually exists. Concretely, it answers:
- Does every
collection_id,parent_id,dashboard_id,document_id,based_on_card_id, transform tag, snippet name, etc. resolve to an entity that actually exists in the tree? - For each MBQL query, do every
source-table, field reference, join target, segment, measure, and expression resolve against the database schema? (Verified by compiling the query to SQL.) - For each native query, do the referenced tables, columns, and snippets exist?
- Do dashboards' and documents' embedded card references point at real cards?
Each run takes 1 minute or more — roughly a minute of fixed JVM + metadata-loading overhead before any checks start, plus query-compilation time that scales with the tree.
The checker ships inside the Metabase Enterprise JAR and is invoked via --mode checker. Default Docker image: metabase/metabase-enterprise:latest. Use metabase/metabase-enterprise-head:latest only when the user explicitly wants the in-development build — e.g. testing unreleased checker changes.
Inputs
Two inputs, both required:
- The representation tree — the repo root containing
collections/,databases/,transforms/,python_libraries/. This is what gets checked. - The database metadata — a JSON file exported from a Metabase instance. By default located at
.metadata/table_metadata.json. The checker uses it to resolve column/table references inside queries; without it, query-level checks cannot run.
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.
- 11d ago First seen · 83 lines · 121 tokens per session scan A f104da27a706
metabase-semantic-checker is a skill published in the GitHub repository metabase/agent-skills (42 stars, last pushed 16d ago), licensed MIT. It adds 121 tokens to every session and 1,488 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…