source-mapping

source-mapping is a skill for Claude Code, Codex from Kemetra/Seshat-BI. It costs 122 tokens per session (2,762 once invoked), scanned A, original, Apache-2.0.

A gate for profiling and documenting a raw retail data table before writing cleaned SQL for it. It records the table’s grain, primary key, and other mapping decisions for review.

In plain words
What is it for?
Use it when onboarding a new source table: profile the data, create the five mapping documents, and stop before producing silver or gold SQL.
Why use it?
It prevents downstream data models from being built on undocumented assumptions and stops work when a human decision or approval is still needed.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/kemetra/seshat-bi/source-mapping
Any agent
npx skills add Kemetra/Seshat-BI --skill source-mapping
Clone the repo
git clone --depth 1 https://github.com/Kemetra/Seshat-BI

Made for: Claude Code, Codex.

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 source-mapping

README.md
[![agentmods](https://agentmods.dev/badge/skills/kemetra/seshat-bi/source-mapping.svg)](https://agentmods.dev/skills/kemetra/seshat-bi/source-mapping)
Your own site
<a href="https://agentmods.dev/skills/kemetra/seshat-bi/source-mapping"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/source-mapping.svg" alt="Measured on agentmods" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,762 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00122 $0.02762
Opus 5 $0.00061 $0.01381
Sonnet 5 $0.00024 $0.00552
Haiku 4.5 $0.00012 $0.00276

Measured 4d ago against content hash a2ae8dcf5ccb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

source-mapping 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 4d 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/source-mapping/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

source-mapping

The source-mapping gate is the kit's one load-bearing rule (constitution Principle IV): before any silver.* SQL is written, the source MUST be profiled and mapped into committed, reviewed artifacts. This skill runs that gate: profile -> author the five artifacts -> stop at judgment calls -> hard-stop before silver. It formalizes Phases 1-4 of the medallion playbook; the playbook stays authoritative on HOW to decide, the templates on WHAT to record.

Scope boundary (read first)

This skill profiles a source and authors the mapping artifacts, then STOPS. It does NOT write silver.* or gold.* SQL, does NOT call pbi-cli or Power BI Desktop, and does NOT decide the judgment calls Principle V reserves for a human. Silver is downstream of an APPROVED map -- approval is the reviewer's action, not this skill's.

The five artifacts (write the blanks with seshat scaffold-source <table>)

Run seshat scaffold-source <table> to materialize the canonical blanks into mappings/<table>/. Do NOT hand-author these files, and do NOT copy from a templates/ path: templates/ exists only in the Seshat development repo, so that instruction fails for anyone who installed the kit as a tool -- and a hand-written source-map.yaml silently misses the canonical shape that seshat validate and the gold stages require (issue #488). The scaffolder ships inside the package and never overwrites an existing file.

Per ADR 0003 (mapping-artifact location), a table's filled set lives in mappings/<table>/:

  1. source-profile.md -- Phase 1 numbers (this skill fills the mechanical ones).
  2. source-map.yaml -- the machine-readable spine (grain+PK first, per-column keep/drop/rename/type/PII/gold-placement, the gold star, derived columns).
  3. assumptions.md -- which RC1-RC16 defaults were ADOPTED vs DEVIATED (each deviation cites its triggering data fact).
  4. unresolved-questions.md -- the build-blocking judgment calls + who answers.
  5. reconciliation-report.md -- the blank the later live run fills (RC16).

Read the full file on GitHub · 194 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. 4d ago First seen · 194 lines · 122 tokens per session scan A a2ae8dcf5ccb

Subscribe to this mod's changes

source-mapping is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 122 tokens to every session and 2,762 once invoked, about $0.0006 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.