datapack-builder

datapack-builder is a skill for Claude Code from anthropics/financial-services. It costs 100 tokens per session (5,330 once invoked), scanned A, original, Apache-2.0.

A workflow for turning financial information from sources such as CIMs, offering memorandums, SEC filings, web searches, or connected services into standardized Excel workbooks. The workbooks are designed for investment committee review.

In plain words
What is it for?
Use it to extract, normalize, check, and format financial data for private equity, investment banking, or asset management analysis.
Why use it?
It reduces manual copying and inconsistent formatting while requiring figures to be traced to their sources and calculations to use formulas.

Skill for Claude Code ✓ vendor

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the investment-banking plugin — 8 skills, 7 commands shipped together

Good fit Use it to extract, normalize, check, and format financial data for private equity, investment banking, or asset management analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anthropics/financial-services/datapack-builder
About the project

Claude for Financial Services is a collection of agents, skills, commands, plugins, and data connectors for investment banking, equity research, private equity, and wealth-management workflows. Financial professionals use it to draft models, memos, research notes, and reconciliations for review by qualified people. The catalogue contains components from these workflows, including agents, skills, plugins, commands, and instructions.

anthropics/financial-services · 34,793 stars · on GitHub

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.

Any agent
npx skills add anthropics/financial-services --skill datapack-builder
Clone the repo
git clone --depth 1 https://github.com/anthropics/financial-services

Made for: Claude Code.

Or install investment-banking, the plugin that ships this one along with the rest of its 8 skills, 7 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 datapack-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/anthropics/financial-services/datapack-builder/github.svg)](https://agentmods.dev/skills/anthropics/financial-services/datapack-builder)
Your own site
<a href="https://agentmods.dev/skills/anthropics/financial-services/datapack-builder"><img src="https://agentmods.dev/badge/skills/anthropics/financial-services/datapack-builder/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.

agentmods 80×15 button for datapack-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/anthropics/financial-services/datapack-builder"><img src="https://agentmods.dev/badge/skills/anthropics/financial-services/datapack-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,330 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 4 May 2026
  • Snyk warn 4 May 2026
How audits are shown
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 5.1 $0.00100 $0.05330
Opus 5 $0.00050 $0.02665
Sonnet 5 $0.00020 $0.01066
Haiku 4.5 $0.00010 $0.00533

Measured today against content hash eb5e83d1a166, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

datapack-builder 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 today.

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.

Origin

Copies of this mod

4 near-identical copies found in the catalogue:

plugins/vertical-plugins/investment-banking/skills/datapack-builder/SKILL.md · 657 lines

How it starts

The opening of the file, as written. The whole thing — 657 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Financial Data Pack Builder

Build professional, standardized financial data packs for private equity, investment banking, and asset management. Transform financial data from CIMs, offering memorandums, SEC filings, web search, or MCP server access into polished Excel workbooks ready for investment committee review.

Important: Use the xlsx skill for all Excel file creation and manipulation throughout this workflow.

CRITICAL SUCCESS FACTORS

Every data pack must achieve these standards. Failure on any point makes the deliverable unusable.

1. Data Accuracy (Zero Tolerance for Errors)

  • Trace every number to source document with page reference
  • Use formula-based calculations exclusively (no hardcoded values)
  • Cross-check subtotals and totals for internal consistency
  • Verify balance sheet balances: Assets = Liabilities + Equity
  • Confirm cash flow ties to balance sheet changes

2. ESSENTIAL RULES

RULE 1: Financial data (measuring money) → Currency format with $ Triggers: Revenue, Sales, Income, EBITDA, Profit, Loss, Cost, Expense, Cash, Debt, Assets, Liabilities, Equity, Capex Format: $#,##0.0 for millions, $#,##0 for thousands Negatives: $(123.0) NOT -$123

RULE 2: Operational data (counting things) → Number format, NO $ Triggers: Units, Stores, Locations, Employees, Customers, Square Feet, Properties, Headcount Format: #,##0 with commas Negatives: (123) consistent with rest of table

RULE 3: Percentages (rates and ratios) → Percentage format Triggers: Margin, Growth, Rate, Percentage, Yield, Return, Utilization, Occupancy Format: 0.0% for one decimal place Display: 15.0% NOT 0.15

RULE 4: Years → Text format to prevent comma insertion Format: Text or custom to prevent 2,024 Display: 2020, 2021, 2022, 2023A, 2024E

RULE 5: When context is mixed, each metric gets its own appropriate format Example:

Segment Analysis, 2022, 2023, 2024
Retail Revenue, $50.0, $55.0, $60.0
  Stores, 100, 110, 120
  Revenue per Store, $0.5, $0.5, $0.5

Revenue and per-store metrics use $, Store count uses number format.

Read the full file on GitHub · 657 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. today First seen · 657 lines · 100 tokens per session scan A eb5e83d1a166

Subscribe to this mod's changes

datapack-builder is a skill published in the GitHub repository anthropics/financial-services (34,793 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 5,330 once invoked, about $0.0005 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 2026-09-12.