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 agentmods add skills/datarails/dr-claude-code-plugins-re/drilldownnpx skills add Datarails/dr-claude-code-plugins-re --skill drilldowngit clone --depth 1 https://github.com/Datarails/dr-claude-code-plugins-reWrote 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/datarails/dr-claude-code-plugins-re/drilldown)<a href="https://agentmods.dev/skills/datarails/dr-claude-code-plugins-re/drilldown"><img src="https://agentmods.dev/badge/skills/datarails/dr-claude-code-plugins-re/drilldown.svg" alt="Measured on agentmods" 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 | $0.00170 | $0.07954 |
| Opus 5 | $0.00085 | $0.03977 |
| Sonnet 5 | $0.00034 | $0.01591 |
| Haiku 4.5 | $0.00017 | $0.00795 |
Grade B, and why
dr-drilldown scanned grade B with 1 finding 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 3d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
**Connection: none needed.** `drilldown_*` works on an **unconnected** workbook. Do not probe or branch on `isConnected`, and never tell the user a drill is unavailable because the workbook is unconnected. If a drill gen How it starts
The opening of the file, as written. The whole thing — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DR.GET Drill-Down
Drill into any cell that contains Datarails data to see the underlying line-item detail. Works with:
- Cells containing a DR formula directly (
DR.GET/DR.QTD/DR.YTD/DR.MTD/… — any DR function) - Cells containing an Excel formula (SUM, +, -, etc.) whose precedents are DR formula cells
Three paths. In a live Excel context (add-in agent bridge available — Claude for Excel / an open workbook with the add-in), drilling a DR formula cell goes through the add-in's own drill-down via the agent bridge (Step 0 below) — the add-in resolves filters, dates, and totals natively. (Excel context is about the bridge being present, not whether the workbook is connected.) The MCP/openpyxl workflow (Phases 0–5) is the file fallback for Claude Code with an .xlsx file and no bridge. And with no workbook at all, no-file mode (below) takes a pasted DR.GET formula, a plain-language description, or structured filters straight from chat.
Requirements (fallback path only): the MCP/openpyxl workflow requires Python with openpyxl to read Excel formulas. If not installed, run pip install openpyxl. The fallback path runs in Claude Code (not Cowork). The Excel-context path needs no Python.
Arguments
| Argument | Description | Default |
|---|---|---|
<cell-reference> |
The cell to drill down on, e.g. B6 or Sheet1!B6 |
Required for the Excel-context and file paths (not used in no-file mode) |
--by <fields> |
Fields to break down by (e.g. Account Full,Vendor). MCP/openpyxl fallback accepts a comma-separated list (multiple dimensions). Excel-context agent pivot (drilldown_by_pivot) takes exactly one field — pass the single field as rowField; if multiple are given, use the first and tell the user the others aren't supported in one pivot. |
All available fields (fallback) / first field (agent pivot) |
--file <path> |
Path to the .xlsx workbook file |
Ask user (omit for no-file mode: pasted formula / description / structured filters) |
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.
- 3d ago First seen · 493 lines · 170 tokens per session scan B 0a5d2ecd871b
dr-drilldown is a skill published in the GitHub repository Datarails/dr-claude-code-plugins-re (3 stars, last pushed 4d ago), licensed MIT. It adds 170 tokens to every session and 7,954 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
xlsx-author
Produce a .xlsx file on disk (headless) instead of driving a live Excel workbook — for managed-agent sessions with no open Office app.
audit-xls
Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this…
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
excel-helper
Excel 表格助手 - 公式编写、数据透视表、图表可视化、宏自动化、数据清洗.