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.
/plugin marketplace add debabsah/analytics-officenpx agentmods add plugins/debabsah/analytics-office/marketplacegit clone --depth 1 https://github.com/debabsah/analytics-officeGrade A, and why
analytics-office 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 2d 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 — 17 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "analytics-office",
"description": "A discipline harness for AI-assisted analytics: a bench of expert BI skills, each read-only and writing to one living knowledge base you resume from. Skills: groundwork (orientation), requirements-interrogator (requirements), kpi-contract (metric definitions), model-contract (dimensional model design), audit-my-assumptions (assumption pre-flight), audit-my-experiment (experiment validity), audit-my-forecast (forecast/time-series validity), review-my-query (query review), triage-my-number (diagnosis), kb-reconcile (knowledge-base audit), brief-my-findings (findings brief & stakeholder updates), defend-my-number (meeting prep & defensibility), status-truth (provenance-graded status reports), explore-my-data (harnessed exploration), map-my-estate (provenance-graded ER/lineage maps), change-impact (pre-flight blast radius), review-my-dashboard (the assembly review), prove-my-parity (stratified tie-out proofs), worth-knowing (the no-ask question charter).",
"owner": { "name": "debabsah" },
"plugins": [
{
"name": "analytics-office",
"description": "A discipline harness for AI-assisted analytics, a bench of skills that grows by accretion — each read-only, all writing to one living knowledge base you (or the next agent) resume from. Skills:'groundwork' (orient on an inherited estate and build a living knowledge base), 'requirements-interrogator' (drive a solution-shaped request to the real decision before building), 'kpi-contract' (pin a metric's exact definition and lock it as a versioned contract), 'defend-my-number' (rehearse defending a number against a skeptic before the meeting), 'review-my-query' (review the query or model behind a number against its locked definition, read-only), 'brief-my-findings' (compose a findings brief or stakeholder update with every claim sourced and graded and open questions kept open, read-only), 'triage-my-number' (diagnose why a number is wrong or moved unexpectedly acWhat ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 17 lines scan A b17bbc8168e4
analytics-office is a plugin published in the GitHub repository debabsah/analytics-office (9 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
seshat-bi-marketplace
Plugin marketplace listing 1 plugin: seshat-bi.
misata
Plugin marketplace listing 1 plugin: misata.
marketplace
Plugin marketplace listing 1 plugin: drizzle-cube.
power-bi-agentic-development
Plugin marketplace listing 11 plugins: goblin-mode, tabular-editor, pbi-desktop, pbip, semantic-models.
custom-visuals
Build Deneb, Python, R, SVG, and pbiviz custom visuals for Power BI.
etl
Inspect, query, and transform lakehouse data with Spark, Livy, and DuckDB.