audit-xls

audit-xls is a skill for Claude Code from anthropics/financial-services. It costs 104 tokens per session (1,545 once invoked), scanned A, original, Apache-2.0.

A spreadsheet-checking skill that looks for formula errors, inconsistent calculations, and common modelling mistakes. It can inspect a selected range, one sheet, or a whole workbook.

In plain words
What is it for?
Use it to review formulas, find overwritten or missing calculations, check ranges, and quality-assure financial models such as DCF, LBO, or three-statement workbooks.
Why use it?
It helps find broken or unreliable calculations before a spreadsheet is shared or used for decisions. For financial models, it also checks whether linked statements and cash figures agree.

Skill for Claude Code ✓ vendor

Written for Claude Code: shipped in a Claude Code plugin.

Part of the earnings-reviewer plugin — 6 skills, 1 agent shipped together

Good fit Use it to review formulas, find overwritten or missing calculations, check ranges, and quality-assure financial models such as DCF, LBO, or three-statement workbooks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anthropics/financial-services/audit-xls
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 · 34,762 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 audit-xls
Clone the repo
git clone --depth 1 https://github.com/anthropics/financial-services

Made for: Claude Code.

Or install earnings-reviewer, the plugin that ships this one along with the rest of its 6 skills, 1 agent.

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 audit-xls

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/anthropics/financial-services/audit-xls"><img src="https://agentmods.dev/badge/skills/anthropics/financial-services/audit-xls.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,545 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 pass 4 May 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium analysis-evasion · line 1
    Suspicious Unicode normalization or mixed-script content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
  • medium Excessive Agency · line 147
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00104 $0.01545
Opus 5 $0.00052 $0.00772
Sonnet 5 $0.00021 $0.00309
Haiku 4.5 $0.00010 $0.00154

Measured 9d ago against content hash df771f6b90fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

audit-xls 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 9d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

  • audit-xls — 100% identical, 0 lines differ
  • audit-xls — 100% identical, 0 lines differ
plugins/agent-plugins/earnings-reviewer/skills/audit-xls/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Spreadsheet

Audit formulas and data for accuracy and mistakes. Scope determines depth — from quick formula checks on a selection up to full financial-model integrity audits.

Step 1: Determine scope

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

What scope do you want me to audit?

  • selection — just the currently selected range
  • sheet — the current active 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 before sending to a client or IC.


Step 2: Formula-level checks (ALL scopes)

Run these regardless of scope:

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

Step 3: Model-integrity checks (MODEL scope only)

If scope is model, identify the model type (DCF / LBO / 3-statement / merger / comps / custom) and run the appropriate integrity checks below.

3a. Structural review

Check What to look for
Input/formula separation Are inputs clearly separated from calculations?
Color convention Blue=input, black=formula, green=link — or whatever the model uses, applied consistently?
Tab flow Logical order (Assumptions → IS → BS → CF → Valuation)?
Date headers Consistent across all tabs?
Units Consistent (thousands vs millions vs actuals)?

Read the full file on GitHub · 157 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. 9d ago First seen · 157 lines · 104 tokens per session scan A df771f6b90fc

Subscribe to this mod's changes

audit-xls is a skill published in the GitHub repository anthropics/financial-services (34,762 stars, last pushed 14d ago), licensed Apache-2.0. It adds 104 tokens to every session and 1,545 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 2026-08-30.