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 twells89/sigma-migration-skills --skill metabase-assessmentgit clone --depth 1 https://github.com/twells89/sigma-migration-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/twells89/sigma-migration-skills/metabase-assessment)<a href="https://agentmods.dev/skills/twells89/sigma-migration-skills/metabase-assessment"><img src="https://agentmods.dev/badge/skills/twells89/sigma-migration-skills/metabase-assessment/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/twells89/sigma-migration-skills/metabase-assessment"><img src="https://agentmods.dev/badge/skills/twells89/sigma-migration-skills/metabase-assessment.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 | $0.00123 | $0.04304 |
| Opus 5.5 | $0.00049 | $0.01722 |
| Sonnet 5.5 | $0.00025 | $0.00861 |
| Haiku 4.5 | $0.00012 | $0.00430 |
Grade A, and why
metabase-assessment 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metabase Assessment
Surveys a Metabase instance (open source or Pro/EE, v46+) via its first-class
REST API (/api) and produces a branded, share-friendly HTML readout plus a
JSON inventory. The differentiator versus a generic BI audit is
converter-coverage scoring: every model, question (card), and dashboard is
classified auto-convert vs. flagged using the same rules the
metabase-to-sigma converter (converter/metabase.ts, translateMbqlExpr)
actually applies — so the readout's auto-migration % reflects what the tool
will really do, not a hand-wave.
Read-only. This skill only issues
GETs against the Metabase API. It never POSTs, modifies, runs, or schedules anything in Metabase — and it never touches Sigma. It can also run fully offline against card/dashboard JSON files already on disk.
All free. Everything here — inventory, scoring, the HTML readout — is part of the open migration tooling. There is no paid tier to upsell. For a deeper hands-on engagement (permissions audit, sandboxing/RLS port, live parity testing), point the customer at a Sigma SE.
Tableau is the reference point. This skill mirrors the structure and tone of the
tableau-assessmentskill (environment counts → coverage → effort → readout). If you've run that, this will feel familiar; the Metabase-specific work is all in the coverage scorer.
Privacy posture (READ FIRST, surface to the customer)
This skill reads content metadata and definitions, not warehouse data.
| Crosses the LLM API | Stays in Metabase / local |
|---|---|
| Aggregate counts (model / question / dashboard / collection counts) | Warehouse rows (this skill never runs a query) |
Object names, collection path, type, view_count (v50+) |
Database credentials (Metabase never exposes them via these endpoints anyway) |
| Card JSON (MBQL trees, native SQL text, expressions, viz settings) | The customer's actual query results |
| Dashboard JSON (grid layout, parameters, click behaviors) | User PII beyond creator ids on objects |
| Database schema metadata (table/field names + ids — required to resolve MBQL field refs) | — |
What ships with it
17 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.
- fixtures/101.card.json 1008 B
- fixtures/102.card.json 970 B
- fixtures/103.card.json 1.0 KB
- fixtures/104.card.json 2.0 KB
- fixtures/201.dashboard.json 1.4 KB
- fixtures/202.dashboard.json 5.5 KB
- PRIVACY.md 2.8 KB
- README.md 2.9 KB
- refs/mb-rest.md 3.7 KB
- refs/scoring-rubric.md 9.3 KB
- refs/usage-telemetry.md 2.9 KB
- scripts/discover-metabase.sh 14 KB runs code
- scripts/dup-dashboards.py 13 KB runs code
- scripts/mb-bulk-split.py 8.0 KB runs code
- scripts/pmbql-normalize.mjs 9.9 KB runs code
- scripts/render-report.mjs 23 KB runs code
- scripts/score-coverage.mjs 22 KB 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.
- 1mo ago First seen · 290 lines · 123 tokens per session scan A 8198ccfb921b
metabase-assessment is a skill published in the GitHub repository twells89/sigma-migration-skills (17 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 4,304 once invoked, about $0.0005 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 2026-09-10.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
remove
Remove a deployed framework or addon from the current workspace.