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-modular-embedding-to-modular-embedding-sdk-upgradegit 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-modular-embedding-to-modular-embedding-sdk-upgrade)<a href="https://agentmods.dev/skills/metabase/agent-skills/metabase-modular-embedding-to-modular-embedding-sdk-upgrade"><img src="https://agentmods.dev/badge/skills/metabase/agent-skills/metabase-modular-embedding-to-modular-embedding-sdk-upgrade/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-modular-embedding-to-modular-embedding-sdk-upgrade"><img src="https://agentmods.dev/badge/skills/metabase/agent-skills/metabase-modular-embedding-to-modular-embedding-sdk-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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.
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 | $0.00078 | $0.03895 |
| Opus 5 | $0.00039 | $0.01947 |
| Sonnet 5 | $0.00016 | $0.00779 |
| Haiku 4.5 | $0.00008 | $0.00390 |
Grade A, and why
metabase-modular-embedding-to-modular-embedding-sdk-upgrade 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execution contract
Follow the workflow steps in order — do not skip any step. Create the checklist first, then execute each step and explicitly mark it done with evidence. Each step's output feeds into the next, so skipping steps produces wrong migrations.
If you cannot complete a step due to missing info or tool failure, you must:
- record the step as ❌ blocked,
- explain exactly what is missing / what failed,
- stop (do not proceed to later steps).
Required output structure
Your response should contain these sections in this order:
- Step 0: Prerequisites Check
- Step 0.1: Migration Plan Checklist
- Step 1: Project Scan
- Step 2: Target SDK API
- Step 3: Migration Mapping
- Step 4: Applied Code Changes
- Step 5: Typecheck Validation
- Step 6: Final Summary
Each step section should end with a status line:
Status: ✅ completeorStatus: ❌ blocked
Evidence requirements
- Step 0: React detected (dependency + version), Metabase instance version, target SDK version, package manager.
- Step 1: every file with Modular embedding usage (web components, metabaseConfig, embed.js script tag), with matching grep lines.
- Step 2: confirm d.ts loaded in context. List exported components, their props, and the MetabaseProvider config type.
- Step 3: the structured migration mapping — every web component → React component with prop conversions, auth config mapping, and embed.js removal plan.
- Step 4: per file — what was changed and exact diffs applied.
- Step 5: the exact typecheck command run and error summary if any remain.
Credential safety
This migration touches code that may contain API keys, JWTs, or auth configuration values (e.g., window.metabaseConfig). Rules:
- Never output literal secret values — if you encounter a hardcoded API key, token, or secret in the code, reference it by variable name or file location (e.g., "the key in
config.js:12"), never echo the value itself - In code diffs and summaries, use variable references — not the resolved values
- If you find hardcoded secrets, flag them to the user and recommend moving them to environment variables as part of the migration
What ships with it
2 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.
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 · 342 lines · 78 tokens per session scan A 54c02988a44d
metabase-modular-embedding-to-modular-embedding-sdk-upgrade is a skill published in the GitHub repository metabase/agent-skills (42 stars, last pushed 16d ago), licensed MIT. It adds 78 tokens to every session and 3,895 once invoked, about $0.0004 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
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.
api-not-found
Diagnose missing TanStack Table v9 exports, options, state slices, and instance methods. Load before inventing an API when code sees a type error, undefined feature method, absent object key, adapter mismatch, or v8-shaped example.
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.
dashboard-widgets
Author a dashboard widget — a small React component backed by named LangWatchQL queries — from a plain question. Discovers the analytics schema, writes the queries, writes the widget file, saves it, then proves it renders. Use when asked to build, prototype, or iterate on a custom chart widget, or to add a widget…