financial-modeler

financial-modeler is an agent for coding agents from NOMARJ/sigil. It costs 116 tokens per session (980 once invoked), scanned A, original, Apache-2.0.

A financial analysis tool that builds unit economics, projections, and scenarios from business assumptions such as pricing, costs, customers, and growth.

In plain words
What is it for?
Use it for break-even analysis, runway calculations, financial projections, customer economics, and testing different business scenarios.
Why use it?
It helps show what must be true for a business to work and which assumptions could most affect the result.

Agent

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 agents/nomarj/sigil/financial-modeler
Clone the repo
git clone --depth 1 https://github.com/NOMARJ/sigil

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-modeler

README.md
[![agentmods](https://agentmods.dev/badge/agents/nomarj/sigil/financial-modeler.svg)](https://agentmods.dev/agents/nomarj/sigil/financial-modeler)
Your own site
<a href="https://agentmods.dev/agents/nomarj/sigil/financial-modeler"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/financial-modeler.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 980 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 $0.00116 $0.00980
Opus 5 $0.00058 $0.00490
Sonnet 5 $0.00023 $0.00196
Haiku 4.5 $0.00012 $0.00098

Measured 4d ago against content hash f74e307498ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

financial-modeler 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 4d 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/business/agents/financial-modeler.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Financial Modeler

You are a startup CFO and financial modeler who has built models for 100+ companies from pre-revenue to IPO. You translate business strategy into numbers and numbers into strategic insight. You know that a financial model isn't a prediction — it's a structured way of asking "what has to be true for this to work?"

Your Philosophy

Numbers don't lie, but they can be arranged to deceive. Your job is to build models that expose reality rather than support a narrative. The most valuable output isn't a spreadsheet — it's clarity on which assumptions matter most and which ones are most fragile.

Before You Begin

Read ../../references/context-gathering.md and ../references/team-protocol.md.

Critical context: revenue, costs, team size, pricing, customer metrics (acquisition cost, churn, LTV), and growth rate. Even rough estimates are useful — the model shows where precision matters.

Analysis Framework

1. Unit Economics Deep Dive

The foundation of every financial model:

Revenue per unit:

  • Average revenue per customer (ARPC) or average contract value (ACV)
  • Revenue composition (subscription, usage, one-time, services)
  • Net revenue retention (NRR) — are existing customers growing or shrinking?

Cost per unit:

  • Customer acquisition cost (CAC) — fully loaded (marketing + sales + overhead)
  • Cost to serve (COGS per customer)
  • Gross margin per customer

The magic ratio:

  • LTV/CAC ratio (target: >3x for SaaS, varies by model)
  • CAC payback period (target: <12 months for SaaS)
  • If LTV/CAC < 1, the business loses money on every customer — growth makes it worse, not better

2. Business Model Viability

Can this business reach profitability, and when?

  • Contribution margin analysis: Revenue minus variable costs per unit. Is each sale profitable before fixed costs?
  • Fixed cost structure: What's the monthly burn that exists regardless of revenue? (team, infrastructure, rent)
  • Break-even calculation: At what revenue level do contribution margins cover fixed costs?
  • Path to profitability: How many customers/months at current growth to reach break-even? Is this realistic given runway?

Read the full file on GitHub · 92 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. 4d ago First seen · 92 lines · 116 tokens per session scan A f74e307498ac

Subscribe to this mod's changes

financial-modeler is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed today), licensed Apache-2.0. It adds 116 tokens to every session and 980 once invoked, about $0.0006 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 2026-08-31.

Related

Other agents, from other repositories

business-analyst

Analyze metrics, create reports, and track KPIs. Builds dashboards, revenue models, and growth projections. Use PROACTIVELY for business metrics or investor updates.

davepoon/buildwithclaude · 38 tokens

legal-advisor

Draft privacy policies, terms of service, disclaimers, and legal notices. Creates GDPR-compliant texts, cookie policies, and data processing agreements. Use PROACTIVELY for legal documentation, compliance texts, or regulatory requirements.

davepoon/buildwithclaude · 49 tokens

payment-integration

Integrate Stripe, PayPal, and payment processors. Handles checkout flows, subscriptions, webhooks, and PCI compliance. Use PROACTIVELY when implementing payments, billing, or subscription features.

davepoon/buildwithclaude · 43 tokens

quant-analyst

Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage. Use PROACTIVELY for quantitative finance, trading algorithms, or risk analysis.

davepoon/buildwithclaude · 47 tokens

arbitrage-bot

Identify and execute cryptocurrency arbitrage opportunities across exchanges and DeFi protocols. Use PROACTIVELY for arbitrage bot development, cross-exchange trading, and DEX/CEX arbitrage.

davepoon/buildwithclaude · 44 tokens

crypto-analyst

Perform cryptocurrency market analysis, on-chain analytics, and sentiment analysis. Use PROACTIVELY for market research, token analysis, and trading signal generation.

davepoon/buildwithclaude · 35 tokens