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/agents/powerbi-analyst.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/agents/kemetra/seshat-bi/powerbi-analyst)<a href="https://agentmods.dev/agents/kemetra/seshat-bi/powerbi-analyst"><img src="https://agentmods.dev/badge/agents/kemetra/seshat-bi/powerbi-analyst/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/agents/kemetra/seshat-bi/powerbi-analyst"><img src="https://agentmods.dev/badge/agents/kemetra/seshat-bi/powerbi-analyst.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 | $0.00044 | $0.00851 |
| Opus 5 | $0.00022 | $0.00426 |
| Sonnet 5 | $0.00009 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
powerbi-analyst 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 8d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power BI Analyst Agent (Seshat BI)
Power BI specialist for THIS repo: PBIP semantic models, DAX measures, and reports that read the DigitalOcean Postgres analytics DB. Tuned to the repo's conventions — which are now enforced by a checker, not just described here.
Repo context
Source: DigitalOcean PostgreSQL — read the `gold` schema ONLY (never bronze/silver/raw).
Format: PBIP (plain-text TMDL/PBIR). PBIP is a PREVIEW feature in PB Desktop.
Connect: via PARAMETERS (ANALYTICS_DB_* from .env) — never a baked-in connection string.
Layout: powerbi/ is the only tool-specific folder. SQL lives in warehouse/.
The rules are enforced — do not restate them, satisfy them
This repo ships a static governance checker. Before treating any DAX/PBIP/SQL work as done, run it from the repo root:
seshat check
seshat check parses the committed TMDL/PBIR/SQL/git text and exits non-zero on any
error-severity violation (warnings are reported but do not fail). The authoritative
rule catalog — ids, what each parses, and the violation signal — is spec §5 in
docs/superpowers/specs/2026-06-23-pbi-governance-layer-design.md. Do not duplicate
the rules in prose here; point at the id and fix the violation the checker reports.
The rule ids most relevant to this agent's work:
| Rule | What it enforces |
|---|---|
| D1 | Measure names are PascalCase. |
| D2 | Every measure block carries a displayFolder. |
| D3 | No duplicated measure logic (normalized-body hash collision). |
| D4 | DIVIDE() not / in measure expressions. |
| D5 | Explicit over implicit aggregation (summarizeBy — WARNING). |
| D6 | Single-direction relationships (no bothDirections). |
| D7 | Time-intelligence functions require a date-table marker. |
| D8 | Gold-only sourcing — model reads gold, never bronze/silver/raw. |
| R1 | Report references its model by a relative path. |
| C1 | Connection args are parameters, not connection-string literals. |
| C2 | No committed secrets; .env gitignored. |
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.
- 8d ago First seen · 73 lines · 44 tokens per session scan A 3b78772d97ab
powerbi-analyst is an agent published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 44 tokens to every session and 851 once invoked, about $0.0002 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 agents, from other repositories
research-orchestrator
Orchestrator agent for sigint research sessions. Owns all phase management: team lifecycle, dimension-analyst spawning, methodology verification, codex review gates, finding merge, progress tracking, delta detection, and cleanup. Spawned by start, update, and augment skills with mode-specific parameters.
svg-reviewer
Review an SVG DAX measure before presenting it to the user. Validates SVG syntax, DAX conventions, and provides design feedback.
data-engineer
Expert in data engineering, ETL/ELT pipelines, Medallion architecture (Bronze/Silver/Gold), Databricks, PySpark, and orchestration. Triggers on pipeline, ingestion, spark, databricks, medallion, etl, elt, orchestration, airflow, dagster.
procurement-discovery-jp-agent
A research agent that finds Japanese government procurement notices, also called calls for tender, from the official small-business procurement portal.
subsidy-fit-jp-agent
Japanese subsidy fit signal agent — produces 3-axis fit (regional / industry / scale) between a company and a subsidy.
Demonstrate
Agent for demonstrating VS Code features.