financial-ops

financial-ops is a skill for Claude Code, Codex from NOMARJ/sigil. It costs 0 tokens per session (2,281 once invoked), scanned A, original, Apache-2.0.

A spreadsheet audit and cleanup skill for financial models and messy data. It checks formulas and model logic, and can normalize text, dates, types, and duplicates in Excel files.

In plain words
What is it for?
Use it to audit formulas, check whether a financial model balances, validate financial logic, clean spreadsheet data, remove duplicates, normalize dates and formatting, and produce a reviewable copy.
Why use it?
It helps find formula errors, hardcoded values, inconsistencies, balance problems, and untidy data before analysis or reporting. Cleaned or audited copies are written separately from the original when requested.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

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/nomarj/sigil/financial-ops
Any agent
npx skills add NOMARJ/sigil --skill financial-ops
Clone the repo
git clone --depth 1 https://github.com/NOMARJ/sigil

Made for: Claude Code, Codex.

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 financial-ops

README.md
[![agentmods](https://agentmods.dev/badge/skills/nomarj/sigil/financial-ops.svg)](https://agentmods.dev/skills/nomarj/sigil/financial-ops)
Your own site
<a href="https://agentmods.dev/skills/nomarj/sigil/financial-ops"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/financial-ops.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,281 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00000 $0.02281
Opus 5 $0.00000 $0.01141
Sonnet 5 $0.00000 $0.00456
Haiku 4.5 $0.00000 $0.00228

Measured 6d ago against content hash bbbfc663bc79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

financial-ops 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 6d 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.

packs/data/skills/data-engineering/financial-ops/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Financial Spreadsheet Operations

description: Two capabilities in one skill — audit spreadsheets for formula accuracy and model integrity, and clean messy data for analysis. Covers formula-level checks (errors, hardcodes, inconsistencies), full financial model audits (BS balance, cash tie-out, logic sanity), and data cleanup (whitespace, casing, duplicates, type coercion, date normalization). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this spreadsheet", "model check", "model won't balance", "clean this data", "normalize this data", "fix formatting", "dedupe", "this data is messy".

Environment

  • Standalone .xlsx file: Use Python/openpyxl. Read cell values and formulas programmatically.
  • If asked to generate a cleaned/audited copy: Write to a new file, never overwrite the original without explicit permission.

No paid MCP dependencies. All operations use openpyxl or pandas — nothing that requires a subscription or external API.


Part A: Spreadsheet Audit

Audit formulas and data for accuracy and mistakes. Scope determines depth.

Step 1: Determine Scope

If the user already gave a scope, use it. Otherwise ask:

What scope do you want me to audit?

  • selection — just a specific range (e.g. A1:F200)
  • sheet — one sheet only
  • model — the whole workbook, including financial-model integrity checks (BS balance, cash tie-out, roll-forwards, logic sanity)

The model scope is the deepest — use it for DCF, LBO, 3-statement, merger, comps, or any integrated financial model.

Step 2: Formula-Level Checks (ALL scopes)

Check What to look for
Formula errors #REF!, #VALUE!, #N/A, #DIV/0!, #NAME?
Hardcodes inside formulas =A1*1.05 — the 1.05 should be a cell reference
Inconsistent formulas A formula that breaks the pattern of its neighbors in a row/column
Off-by-one ranges SUM/AVERAGE that misses the first or last row
Pasted-over formulas Cell that looks like a formula but is actually a hardcoded value
Circular references Intentional or accidental
Broken cross-sheet links References to cells that moved or were deleted
Unit/scale mismatches Thousands mixed with millions, % stored as whole numbers
Hidden rows/tabs Could contain overrides or stale calculations

Read the full file on GitHub · 211 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. 6d ago First seen · 211 lines · 0 tokens per session scan A bbbfc663bc79

Subscribe to this mod's changes

financial-ops is a skill published in the GitHub repository NOMARJ/sigil (5 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,281 tokens. 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.