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/dashboard-intelligence/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/dashboard-intelligence)<a href="https://agentmods.dev/skills/kemetra/seshat-bi/dashboard-intelligence"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/dashboard-intelligence/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/dashboard-intelligence"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/dashboard-intelligence.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 | $0.00213 | $0.02599 |
| Opus 5.5 | $0.00085 | $0.01040 |
| Sonnet 5.5 | $0.00043 | $0.00520 |
| Haiku 4.5 | $0.00021 | $0.00260 |
Grade A, and why
dashboard-intelligence 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dashboard-intelligence
The coordinator for the governed dashboard-intelligence journey (spec 123, US2). Seshat already ships strong, individually-governed dashboard components; today a user must wire them by hand and can reach visual implementation without a committed report purpose. This skill turns that set of skills into ONE coherent, fail-closed sequence: given an approved Report Intent (US1), approved metric contracts, and a ready semantic model, it sequences the shipped capabilities in the correct order to produce a reviewable dashboard design, and STOPS at the human blueprint-review seam.
You (the agent reading this) ARE the runtime. This skill is procedure, not an engine:
there is no daemon, no scheduler, no persisted counter. The self-heal loop below is
something YOU perform in-context, exactly like retail-orchestrate.
Scope + non-negotiables (read first)
- Compose, never fork (FR-008/FR-011). Reuse the shipped capabilities as they
are. Do NOT re-implement gap detection, planning, or design, and do NOT introduce a
broad new CLI family to wrap them. The one small helper this skill leans on --
src/seshat/dashboard_coordinator.py-- is a READ-ONLY state inspector, not a new verb; it decides the next allowed action and names any blocker. - The hard gate is
semantic_model_ready: pass(FR-010). Never design a data-bound visual before it.warning/blocked/not_startedall FAIL the gate. The coordinator reads the gate; it never bypasses it and never re-derives it. - No self-grant of
dashboard_ready: pass(FR-010, Principle V). The highest outcome a happy path reaches is "STOP at the human blueprint review". Thedashboard_blueprint_approvaldecision is a NAMED-human action recorded in the shipped Decision Store -- an agent identity never satisfiesapproved_by. - Fail closed (FR-033/FR-034). On any unmet precondition, STOP with a blocked result that NAMES: (1) what is missing/invalid; (2) the evidence checked; (3) the responsible owner; (4) the action that would unblock progress. Never a numeric score (FR-035). Never proceed past a stop to "make progress".
- Read-only + static (SEC-001). No live DB, no Power BI Desktop, no PBIR authoring, no publish/refresh/export. The journey stops at committed on-disk artifacts; execution is the deferred F016 boundary.
- ASCII only, UTF-8 no BOM in anything you author (
->arrows).
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 · 159 lines · 213 tokens per session scan A 4b728edc4dab
dashboard-intelligence is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 213 tokens to every session and 2,599 once invoked, about $0.0009 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.