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/retail-semantic-check/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/retail-semantic-check)<a href="https://agentmods.dev/skills/kemetra/seshat-bi/retail-semantic-check"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/retail-semantic-check/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/kemetra/seshat-bi/retail-semantic-check"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/retail-semantic-check.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 | $0.00186 | $0.03821 |
| Opus 5 | $0.00093 | $0.01911 |
| Sonnet 5 | $0.00037 | $0.00764 |
| Haiku 4.5 | $0.00019 | $0.00382 |
Grade A, and why
retail-semantic-check 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
retail-semantic-check
seshat check proves the model is mechanically clean (PascalCase measures, display
folders, DIVIDE, single-direction relationships, a marked date table, gold-only
partitions, parameterized connection, no real host). This skill answers the larger
question that clean text alone cannot: is the semantic model GOVERNED -- does
every measure trace to an APPROVED metric contract, with the gold star already
live-validated underneath it? It computes the Stage-5 verdict and STOPS -- the live
sibling of retail-govern / retail-validate, one layer up: it governs the SEMANTIC
MODEL, not the SQL. It implements the procedure that
docs/readiness/semantic-model-ready.md specifies; it redefines nothing.
Scope boundary (read first)
Invoke-and-interpret only, and READ-ONLY.
- CHECKS the model. Reads the committed PBIP TMDL, reads the filled
metric-contract store, runs
seshat check, evaluates the contract-binding criterion, and emits one readiness verdict. All side-effect-free reads over committed text -- the same category asretail-governreading TMDL. - NEVER DEFINES contracts (F009). The metric-contract store (name, grain, formula
intent, owner, approval) is defined and owned by feature F009 (the
metric-contracttemplate + themetric-contract-storeguide). This skill is the CONSUMER: it reads contracts to test the binding; it never creates, edits, or approves one. - NEVER AUTHORS or EXECUTES the model (F016, deferred + gated). It writes no TMDL, adds/edits
no measure / relationship / date marker, opens no DB connection, and calls no
the Power BI execution adapter (official Power BI MCP / connection;
pbi-clino longer preferred) (constitution Principle II; roadmap hard rule #6 -- F016 is last and gated on THIS stage beingpass). It reads an EXISTING model and reports; a human edits Power BI Desktop and re-saves the PBIP to remediate.
Prerequisites
- The prior stage Gold Ready is
pass-- read it from the canonicalmappings/<table>/readiness-status.yaml(ADR 0004; shaped totemplates/readiness-status.yaml). This stage sits AFTER the live-validation hard gate (no gold to Power BI before validation, roadmap rule #4). If Gold Ready is notpass, the verdict isnot_startedand the skill STOPS. - The committed PBIP model exists under
powerbi/<Model>.SemanticModel/definition/. - The metric-contract store (F009) -- the FILLED, per-table contracts -- may or may
not exist. Its absence is not an error; it is the reason the verdict is
blocked(see the central property below).
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 · 263 lines · 186 tokens per session scan A 9cf796acbc41
retail-semantic-check is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 186 tokens to every session and 3,821 once invoked, about $0.0009 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.