Borrowing it
Nothing to install: this file belongs to Kemetra/Seshat-BI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Kemetra/Seshat-BI/main/.claude/skills/consumer-data-dictionary/SKILL.mdgit clone --depth 1 https://github.com/Kemetra/Seshat-BIWrote 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/kemetra/seshat-bi/consumer-data-dictionary)<a href="https://agentmods.dev/skills/kemetra/seshat-bi/consumer-data-dictionary"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/consumer-data-dictionary.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.05654 |
| Opus 5 | $0.00023 | $0.02827 |
| Sonnet 5 | $0.00009 | $0.01131 |
| Haiku 4.5 | $0.00005 | $0.00565 |
Grade A, and why
consumer-data-dictionary 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 7d 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 — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
consumer-data-dictionary
- Roadmap feature: F040 (proposed; the roadmap-ledger row is deferred to
integration time -- see research.md section 1.4; not yet a confirmed
ledger entry). On-disk spec:
specs/101-consumer-data-dictionary/. - Authority category: Product Module /
artifact-writing(the F024 enumerated declaration -- seedocs/architecture/product-modules.md).
Today, "what does this column/measure mean" answers exist but are scattered
across BUILDER-facing artifacts nobody wrote for a self-serve analyst: a gold
column's business meaning lives as a mapping-decision reason string inside
mappings/<table>/source-map.yaml (written for the mapping-gate reviewer, not
a report reader); a measure's plain-language meaning lives as formula_intent
inside mappings/<table>/metrics/<Metric>.yaml (already consumer-legible
prose); and the handoff pack's own data-dictionary section exists to satisfy
the Publish Ready gate, not to serve the analyst who later queries the
published model. This skill is the COMPOSER that assembles those scattered,
already-committed artifacts into ONE ordered, plain-language reference for the
CONSUMER. It FILLS the dictionary; it originates no meaning and owns no truth.
Every entry cites the committed source it came from; where no committed
consumer-legible meaning exists, the entry is an explicit GAP, never invented
prose.
Boundary against neighbouring shipped work (read first)
- F013 BI Handoff Pack (
templates/handoff/bi-handoff-pack.md, item e "Data dictionary") is a REQUIRED section of the Publish Ready (Stage 7) gate bundle: its audience is the data-owner/governance reviewer deciding whether to authorize release, its lifecycle moment is BEFORE publish (gate evidence), and a mismatch against the deployed schema FAILS the checklist. This module's dictionary is an OPTIONAL companion consumed AFTER a table is published, by the analyst querying it self-serve; it adds NO gate, NO blocking reason, and NO required section to Publish Ready (following theanswerability-summary.mdprecedent). It composes from the SAME upstream truth but does not edit, re-render, or duplicate-govern F013's item (e). - F028 evidence-pack-generator (
.claude/skills/evidence-pack-generator/, spec 022) composes a late-stage, 10-section READINESS evidence bundle (blockers, scorecards, approvals) for the Semantic Model -> Dashboard -> Publish window. This module composes a MEANING reference (what a column/ measure means), not a readiness bundle; it carries no blocker list, no stage status, no approval slot, and is not part of any stage'sevidence[]by default. Different output filename (FR-018), no collision. - The
power-bi-docsskill family generates model documentation FROM A LIVE, CONNECTED semantic model (pbi connectrequired). This module is Principle-VIII static-first: it reads only committed, on-disk artifacts and never opens a live Power BI or database connection; any live-schema drift against the deployed model is marked PENDING, never silently assumed reconciled.
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.
- 7d ago First seen · 411 lines · 46 tokens per session scan A 798e244ed5c2
consumer-data-dictionary is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 46 tokens to every session and 5,654 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
ktx-analytics
Use when answering a question that needs data from a ktx-connected database - investigating, analyzing, "how many", "show me", "what's the breakdown of", finding records by value, exploring tables, comparing periods, explaining metrics, or any data-analysis request. Triggers even when the user does not say…
metabase_ingest
Convert Metabase questions, models, and metrics into ktx Semantic Layer source definitions. Covers result-metadata to KSL column type mapping, FK/PK detection, near-duplicate deduplication, pre-aggregation decomposition, join-graph connectivity, and how to react to priorProvenance from earlier ingest syncs. Load when…
sl_capture
How to capture new reusable patterns into ktx's semantic layer - when a measure, segment, or join belongs in the catalog and how to write it generically so it stays small and useful over time. Loaded by the post-turn memory-agent only. The research agent does not write to the SL.
looker_ingest
Extract durable ktx knowledge and semantic-layer contribution proposals from staged Looker runtime dashboard, Look, and explore JSON. Load for WorkUnits whose raw files are under explores/, dashboards/, or looks/.
metricflow_ingest
Map a MetricFlow semanticmodel or metric into ktx semantic layer sources. Covers the MetricFlow to ktx primitive table, extends: inheritance flattening, metric-type handling (simple / derived / ratio / cumulative / conversion), model: ref('x') resolution, and four worked examples. Load when the turn contains…
lookml_ingest
Map a LookML view/model/explore into ktx semantic layer sources. Covers the LookML to ktx primitive table, provenance tagging, and three worked examples (overlay, standalone from derivedtable, standalone with sqlalwayswhere). Load when the turn contains .lkml content.