Seshat-BI: Skill for Claude Code

.claude/skills/retail-semantic-check/SKILL.md

retail-semantic-check is a skill for Claude Code from Kemetra/Seshat-BI. It costs 186 tokens per session (3,821 once invoked), scanned A, original, Apache-2.0.

A read-only check of whether a Power BI semantic model is governed, meaning its measures connect to approved definitions for business metrics.

In plain words
What is it for?
Use it before dashboard work to inspect the model files, metric contracts, and existing checks, then produce a semantic-model readiness decision.
Why use it?
A model can be technically clean but still use measures that are not tied to approved metric definitions. This check identifies that gap after the underlying data is ready.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Kemetra/Seshat-BI's own configuration. It tells Claude Code how to work on Seshat-BI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Seshat-BI configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Kemetra/Seshat-BI/main/.claude/skills/retail-semantic-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Kemetra/Seshat-BI

Made for: Claude Code.

Wrote 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.

agentmods badge for retail-semantic-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/kemetra/seshat-bi/retail-semantic-check/github.svg)](https://agentmods.dev/skills/kemetra/seshat-bi/retail-semantic-check)
Your own site
<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.

agentmods 80×15 button for retail-semantic-check

Your own site · 80×15
<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>
Per session 186 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,821 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 9cf796acbc41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

.claude/skills/retail-semantic-check/SKILL.md · 263 lines

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 as retail-govern reading TMDL.
  • NEVER DEFINES contracts (F009). The metric-contract store (name, grain, formula intent, owner, approval) is defined and owned by feature F009 (the metric-contract template + the metric-contract-store guide). 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-cli no longer preferred) (constitution Principle II; roadmap hard rule #6 -- F016 is last and gated on THIS stage being pass). 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 canonical mappings/<table>/readiness-status.yaml (ADR 0004; shaped to templates/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 not pass, the verdict is not_started and 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).

Read the full file on GitHub · 263 lines

Changes

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.

  1. 11d ago First seen · 263 lines · 186 tokens per session scan A 9cf796acbc41

Subscribe to this mod's changes

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.

Related

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…

Kaelio/ktx · 86 tokens

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…

Kaelio/ktx · 90 tokens

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.

Kaelio/ktx · 63 tokens

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/.

Kaelio/ktx · 44 tokens

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…

Kaelio/ktx · 0 tokens

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.

Kaelio/ktx · 63 tokens