pn-financial-model-audit

pn-financial-model-audit is a skill for Cursor from perniemann/pnCore. It costs 73 tokens per session (1,036 once invoked), scanned A, original, MIT.

A quality check for financial models in spreadsheets, tables, or generated outputs. It looks for typed values that should be formulas, broken calculations, balance-sheet errors, circular references, and missing checks.

In plain words
What is it for?
Use it after building DCF, LBO, comparable-company, or three-statement models, or whenever someone supplies a financial model for review.
Why use it?
It helps catch mistakes before a valuation or forecast is used in a report or decision. The review shows where a problem is and what behavior was expected.

Skill for Cursor

Written for Cursor: shipped in a Cursor plugin.

Part of the pn-core plugin — 133 skills, 19 commands, 9 agents, 1 MCP server shipped together

Good fit Use it after building DCF, LBO, comparable-company, or three-statement models, or whenever someone supplies a financial model for review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/perniemann/pncore/pn-financial-model-audit
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 perniemann/pnCore --skill pn-financial-model-audit
Clone the repo
git clone --depth 1 https://github.com/perniemann/pnCore

Made for: Cursor.

Or install pn-core, the plugin that ships this one along with the rest of its 133 skills, 19 commands, 9 agents, 1 MCP server.

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 pn-financial-model-audit

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/perniemann/pncore/pn-financial-model-audit"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-financial-model-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,036 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.
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 $0.00073 $0.01036
Opus 5 $0.00036 $0.00518
Sonnet 5 $0.00015 $0.00207
Haiku 4.5 $0.00007 $0.00104

Measured 7d ago against content hash 24fe5ea7cee5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pn-financial-model-audit 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 7d 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.

packages/pn-core-mcp/content/skills/fsi/pn-financial-model-audit/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Financial model audit

When to use

  • After pn-dcf-model, pn-comps-analysis, or any LBO / 3-statement build, before the model feeds a deliverable.
  • When a user supplies a spreadsheet or table for review.
  • As a quality gate in a modeling workflow step before proceeding to memo or presentation.

Pre-requisites

Load get_skill("pn-fsi-analyst-discipline"). Identify what was supplied: agent-produced structured output, user-uploaded file, or inline table.

Audit checklist

1. Hardcode detection

  • Scan each row and formula for values that should be calculated but are typed as constants.
  • Common offenders: tax rate typed as a number instead of referencing an assumption cell; D&A that does not roll from a schedule; NWC changes that are zero rather than formula-driven.
  • Flag each hardcode: location (row / column / step), expected behavior, suggested fix.

2. Formula integrity

  • Verify that each calculated line follows from the stated formula (e.g. UFCF = NOPAT + D&A – Capex – ΔNWC).
  • Check for sign errors: cash outflows (capex, NWC increase) must be subtracted; inflows (D&A add-back) added.
  • Check that growth rates are applied to the correct base (prior-year, not base-year, for compound growth).
  • Check that discount factors use consistent periodicity (annual vs. mid-year convention; state which and apply uniformly).

3. Balance checks

For 3-statement models:

  • Assets = Liabilities + Equity (balance sheet check; flag any period that does not balance).
  • Cash flow statement: net change in cash reconciles to balance sheet cash movement.
  • Retained earnings roll: opening RE + Net income – Dividends = Closing RE.

For DCF / LBO:

  • PV of UFCF + PV of TV = EV (verify discounting arithmetic).
  • Equity bridge: EV – Net debt – Minority – Preferred = Equity value.
  • Returns check (LBO): sponsor equity = purchase equity – fees; exit equity = exit EV – exit debt; MOIC = exit equity / sponsor equity.

4. Circular references

  • Flag any circular dependency (e.g. interest expense referencing ending debt, which depends on interest). Note whether it is intentional (iterative solve) and whether iteration is enabled.
  • If not intentional, suggest the decoupling fix.

Read the full file on GitHub · 106 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. 7d ago First seen · 106 lines · 73 tokens per session scan A 24fe5ea7cee5

Subscribe to this mod's changes

pn-financial-model-audit is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 1,036 once invoked, about $0.0004 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 2026-09-03.