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.
npx skills add Kemetra/Seshat-BI --skill pbi-mcp-doctorgit 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/pbi-mcp-doctor)<a href="https://agentmods.dev/skills/kemetra/seshat-bi/pbi-mcp-doctor"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/pbi-mcp-doctor/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/pbi-mcp-doctor"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/pbi-mcp-doctor.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 | $0.00073 | $0.01441 |
| Opus 5 | $0.00036 | $0.00720 |
| Sonnet 5 | $0.00015 | $0.00288 |
| Haiku 4.5 | $0.00007 | $0.00144 |
Grade A, and why
pbi-mcp-doctor 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 9d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power BI MCP doctor (read-only)
Read ../../portable-operating-contract.md before acting. Use only the
installed seshat pbi-mcp verbs; never launch an MCP server directly, never
edit .mcp.json by hand when the generator can produce it, and never treat
any output of this family as an approval. F016 (the Power BI execution
adapter) is PARKED: no mutation path exists anywhere in this family.
Fixed workflow
-
Map the user's task to the governed surface, read-only:
seshat pbi-mcp doctor --repo . --intent <task> [--target <table>] [--harness <claude-code|codex>] [--json] [--write-advisory]--intentis a closed vocabulary:model-edit,published-query,report-authoring,report-formatting,desktop-verification,db-connectivity,ci-validation,sensitive-production. Report the recommendation, its missing prerequisites, and the next HUMAN step verbatim. A blocked recommendation (exit 2) names the gate -- stop there; never route around it.--write-advisoryrecords the result once at.seshat/powerbi-mcp-recommendation.yaml(write-once; it refuses to overwrite) and is never a side effect.report-authoringadditionally requires an exact--target <table>. It selects Microsoft's officialpowerbi-report-authoringskill, but remains blocked until that target has a committed semantic-model pass, a complete named-humandashboard_readyapproval, and the Spec 148 harness probe reports the skill discoverable. Approval does not itself claimdashboard_ready: pass. Installed is not the same as activated. -
Generate config only through the safe generator:
seshat pbi-mcp generate-config [--transport local|remote|both] [--setup-doc] [--out <path>]Output is placeholder-only and read-only (
--readonly); it is secret-scanned before emission and refuses to overwrite an existing file. If it refuses because output would be secret-shaped, stop and report -- never bypass the scan by writing the file yourself.
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.
- 9d ago First seen · 118 lines · 73 tokens per session scan A 6adb62cc355d
pbi-mcp-doctor is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,441 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
azure
Manage Azure cloud resources -- resource groups, storage, databases, functions, and data services using the az CLI.
s3
Manage AWS S3 storage -- list buckets, upload/download files, sync directories, and manage object lifecycle.
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/.
sigma_ingest
Extract durable ktx wiki knowledge from staged Sigma data model specs and workbook summaries. Load for WorkUnits with unitKey sigma-data-models or sigma-workbooks.
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.