dr-drilldown

dr-drilldown is a skill for Claude Code, Codex from Datarails/dr-claude-code-plugins-re. It costs 170 tokens per session (7,954 once invoked), scanned B, original, MIT.

A detailed breakdown of a Datarails figure into the underlying line items behind an Excel cell or financial formula.

In plain words
What is it for?
Use it to investigate a cell, explain a variance, understand what is driving a figure, or review pasted formulas and filters.
Why use it?
It explains what makes up a number or variance instead of leaving you with only the total.

Skill for Claude CodeCodex

Part of the datarails-financeos plugin — 19 skills, 4 commands shipped together

Install

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.

agentmods
npx agentmods add skills/datarails/dr-claude-code-plugins-re/drilldown
Any agent
npx skills add Datarails/dr-claude-code-plugins-re --skill drilldown
Clone the repo
git clone --depth 1 https://github.com/Datarails/dr-claude-code-plugins-re

Made for: Claude Code, Codex.

Or install datarails-financeos, the plugin that ships this one along with the rest of its 19 skills, 4 commands.

Wrote 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.

agentmods badge for dr-drilldown

README.md
[![agentmods](https://agentmods.dev/badge/skills/datarails/dr-claude-code-plugins-re/drilldown.svg)](https://agentmods.dev/skills/datarails/dr-claude-code-plugins-re/drilldown)
Your own site
<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>
Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,954 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 0a5d2ecd871b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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
skills/drilldown/SKILL.md · 493 lines

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)

Read the full file on GitHub · 493 lines

Changes

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.

  1. 3d ago First seen · 493 lines · 170 tokens per session scan B 0a5d2ecd871b

Subscribe to this mod's changes

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.