dcf

dcf is a command for Claude Code from yuping322/financial-services-plugins-new. It costs 11 tokens per session (874 once invoked), scanned A, original, Apache-2.0.

A command for valuing a company by forecasting its future cash and comparing it with similar public companies. DCF means discounted cash flow, a method that converts expected future cash into a value today.

In plain words
What is it for?
Use it to gather company and peer data, build bear, base, and bull forecasts, estimate free cash flow, and calculate a valuation range.
Why use it?
It organizes the research and assumptions needed to estimate a company’s value. Comparable companies provide market-based checks for growth, profit margins, and valuation multiples.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the financial-analysis plugin — 9 skills, 8 commands, 11 MCP servers shipped together

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 commands/yuping322/financial-services-plugins-new/dcf
Clone the repo
git clone --depth 1 https://github.com/yuping322/financial-services-plugins-new

Made for: Claude Code.

Or install financial-analysis, the plugin that ships this one along with the rest of its 9 skills, 8 commands, 11 MCP servers.

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 dcf

README.md
[![agentmods](https://agentmods.dev/badge/commands/yuping322/financial-services-plugins-new/dcf.svg)](https://agentmods.dev/commands/yuping322/financial-services-plugins-new/dcf)
Your own site
<a href="https://agentmods.dev/commands/yuping322/financial-services-plugins-new/dcf"><img src="https://agentmods.dev/badge/commands/yuping322/financial-services-plugins-new/dcf.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 874 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 $0.00011 $0.00874
Opus 5 $0.00005 $0.00437
Sonnet 5 $0.00002 $0.00175
Haiku 4.5 $0.00001 $0.00087

Measured 6d ago against content hash ba4c3e0a2f6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dcf 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.

financial-analysis/commands/dcf.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DCF Valuation Command

Build an institutional-quality DCF model that uses comparable company analysis to inform valuation ranges.

Workflow

Step 1: Gather Company Information

If a company name or ticker is provided, use it. Otherwise ask:

  • "What company would you like to value?"

Step 2: Run Comparable Company Analysis

First, load the comps-analysis skill to build trading comps:

Use skill: "comps-analysis" to:

  1. Identify 4-6 comparable public companies
  2. Pull operating metrics (Revenue, EBITDA, margins, growth)
  3. Pull valuation multiples (EV/Revenue, EV/EBITDA, P/E)
  4. Calculate statistical summary (median, 25th/75th percentiles)

Key outputs to capture from comps:

  • Median EV/EBITDA multiple → informs terminal value exit multiple
  • Median EV/Revenue multiple → sanity check on DCF output
  • Peer growth rates → benchmark for revenue projections
  • Peer margins → benchmark for margin assumptions

Step 3: Build DCF Model

Load the dcf-model skill to construct the valuation:

Use skill: "dcf-model" to:

  1. Gather historical financials and market data
  2. Build revenue projections (Bear/Base/Bull cases)
  3. Model operating expenses and FCF
  4. Calculate WACC using CAPM
  5. Discount cash flows and calculate terminal value
  6. Bridge to equity value and implied share price

Use comps to inform DCF assumptions:

Comps Output DCF Input
Peer median EV/EBITDA Terminal exit multiple range
Peer 25th-75th EV/EBITDA Sensitivity analysis range
Peer median growth rate Benchmark for revenue assumptions
Peer median EBITDA margin Target margin in terminal year
Peer median P/E Cross-check implied P/E from DCF

Step 4: Cross-Check Valuation

After DCF is complete, validate:

  1. Implied EV/EBITDA from DCF vs peer median
    • If DCF implies 25x but peers trade at 12x, investigate why
  2. Implied P/E from DCF vs peer median
  3. Terminal value as % of EV (should be 50-70%)
  4. Implied growth embedded in valuation vs peer growth rates

Read the full file on GitHub · 103 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 · 103 lines · 11 tokens per session scan A ba4c3e0a2f6b

Subscribe to this mod's changes

dcf is a command published in the GitHub repository yuping322/financial-services-plugins-new (17 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 874 once invoked, about $0.0001 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.