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/pbi-mcp-write-adapter/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/pbi-mcp-write-adapter)<a href="https://agentmods.dev/skills/kemetra/seshat-bi/pbi-mcp-write-adapter"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/pbi-mcp-write-adapter/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-write-adapter"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/pbi-mcp-write-adapter.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 | $0.00170 | $0.02586 |
| Opus 5 | $0.00085 | $0.01293 |
| Sonnet 5 | $0.00034 | $0.00517 |
| Haiku 4.5 | $0.00017 | $0.00259 |
Grade A, and why
pbi-mcp-write-adapter 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pbi-mcp-write-adapter
- Authority category (F024): Execution Adapter /
publish-capable, execution-only -- the binding declaration istemplates/pbi-mcp-adapter-contract.md. - Roadmap feature: F016 slice 5 On-disk spec:
specs/149-pbi-mcp-write-adapter - Authorizing decision:
docs/decisions/0018-unpark-f016-power-bi-mcp-execution-adapter.md(ratified by the owner 2026-08-18). All eight ADR decisions bind together; none is severable.
What problem this closes
A user who has taken a semantic model all the way to an approved, signed-off state still had to leave the governed workflow and apply the change by hand in Power BI Desktop. Nothing recorded what was applied, to which target, on whose authority, or whether the artifact still validated afterwards. Microsoft's official Power BI MCP can apply such changes, but its own documentation warns that autonomous or misconfigured clients may perform destructive actions and that its safety flags are non-standard and client-dependent.
So the gap was never "we lack a tool". It was "the available tool's safety model is weaker than the approval spine we already run." This adapter puts Seshat's recorded, named-human approval above the vendor tool rather than trusting the vendor's prompts.
The rule you must not talk yourself out of
You never supply the evidence that permits your own write. Every precondition is derived from committed state, never accepted as something you assert. If you find yourself reasoning "the user said it was approved" or "I already checked that", stop: ask checked against what? If the answer is "what I was told", the gate has not been satisfied.
This is not a style preference. Five separate versions of that exact defect were caught in this feature's own review -- a caller-supplied allowlist, a caller-asserted operation binding, a caller-asserted backup, a permissive git-state default, and a gate that read the working tree (where an agent can write) instead of HEAD.
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.
- 11d ago First seen · 189 lines · 170 tokens per session scan A 69d5160de451
pbi-mcp-write-adapter is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 170 tokens to every session and 2,586 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.
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.