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-orchestrate/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-orchestrate)<a href="https://agentmods.dev/skills/kemetra/seshat-bi/retail-orchestrate"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/retail-orchestrate/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-orchestrate"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/retail-orchestrate.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 | $0.00128 | $0.02824 |
| Opus 5.5 | $0.00051 | $0.01130 |
| Sonnet 5.5 | $0.00026 | $0.00565 |
| Haiku 4.5 | $0.00013 | $0.00282 |
Grade A, and why
retail-orchestrate 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
retail-orchestrate
The conductor for Layer D. The kit's architecture makes the agent the primary surface: "an agent runs the playbook conversationally ... and self-heals against the gate." This skill is how the agent does that -- it sequences the four existing verb-skills across the medallion phases and runs the self-heal loop whose only success signal is a literal gate exit 0.
You (the agent reading this) ARE the runtime. This skill is procedure, not an engine: there is no daemon, no scheduler, no persisted counter, and no fix-applying subagent.
Scope + non-negotiables (read first)
- Agent is the orchestrator. Do not build or invoke a loop runtime, a counter file, or a subagent whose job is "run gate, apply fix, repeat." That is the parked orchestration runtime (architecture open decision #3). The loop below is something YOU perform in-context.
- The gate exit code is the SOLE pass authority (constitution Principle I --
agent proposes, gate disposes). A phase advances ONLY on a literal exit 0 from
seshat check/retail validate. Never declare a rule "passed" from reading prose or your own edit; only the non-zero/zero exit decides. - Fail-closed. A non-zero exit blocks. Never suppress, never promote warnings to pass, never merge around a failing gate.
- Two hard human seams you MUST stop at:
- Mapping gate (Principle IV): no
silver.*until the map is reviewed and approved. Read approval from existing state (below) -- never self-grant it. - Judgment calls (Principle V): grain, PII, business rollup, the authoritative returns column, sentinel-vs-null -- escalate to a human; do not decide them to make a finding go away.
- Mapping gate (Principle IV): no
- ASCII only, UTF-8 no BOM in everything you author (
->arrows,''OR NULL).
Run-state: read mappings// FIRST (no new state file)
Compute the current phase from what is already on disk -- there is NO orchestration state file to create:
| What you observe | Current phase / action |
|---|---|
No mappings/<table>/ dir |
Start at Phase 1 (source-mapping). |
mappings/<table>/readiness-status.yaml missing or stages.mapping_ready.status != pass; or artifacts present with Gate status: OPEN (any open row) in mappings/<table>/unresolved-questions.md |
STOPPED at the mapping gate. Report the open questions; do not advance. |
stages.mapping_ready.status == pass WITH a matching approvals[] entry, and the Gate status: CLEARED (zero open rows) mirror agrees |
Map approved -> resume at the silver [SEAM]. |
warehouse/migrations/ has the table's silver+gold |
Resume at the validate phase. |
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 · 171 lines · 128 tokens per session scan A 75d20c01aca8
retail-orchestrate is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 128 tokens to every session and 2,824 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 2026-08-31.
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.