pitch-analyst

pitch-analyst is an agent for Claude Code from tjboudreaux/cc-skills-vc-fundraising. It costs 72 tokens per session (1,658 once invoked), scanned A, original, MIT.

An analyst for pitch decks and fundraising stories, evaluating how clearly a startup explains its problem, market, progress, timing, and advantage to venture investors.

In plain words
What is it for?
Use it to review pitch structure, sharpen the narrative, assess market sizing and traction, clarify the company’s unique insight, and prepare supporters to explain the business.
Why use it?
It finds weak or confusing parts of an investor presentation and turns them into specific improvements grounded in common venture-investing frameworks.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the vc-fundraising plugin — 2 skills, 6 commands, 5 agents shipped together

Good fit Use it to review pitch structure, sharpen the narrative, assess market sizing and traction, clarify the company’s unique insight, and prepare supporters to explain the business.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tjboudreaux/cc-skills-vc-fundraising/pitch-analyst
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.

Clone the repo
git clone --depth 1 https://github.com/tjboudreaux/cc-skills-vc-fundraising

Made for: Claude Code.

Or install vc-fundraising, the plugin that ships this one along with the rest of its 2 skills, 6 commands, 5 agents.

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 pitch-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/tjboudreaux/cc-skills-vc-fundraising/pitch-analyst/github.svg)](https://agentmods.dev/agents/tjboudreaux/cc-skills-vc-fundraising/pitch-analyst)
Your own site
<a href="https://agentmods.dev/agents/tjboudreaux/cc-skills-vc-fundraising/pitch-analyst"><img src="https://agentmods.dev/badge/agents/tjboudreaux/cc-skills-vc-fundraising/pitch-analyst/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 pitch-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/tjboudreaux/cc-skills-vc-fundraising/pitch-analyst"><img src="https://agentmods.dev/badge/agents/tjboudreaux/cc-skills-vc-fundraising/pitch-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,658 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 $0.00072 $0.01658
Opus 5 $0.00036 $0.00829
Sonnet 5 $0.00014 $0.00332
Haiku 4.5 $0.00007 $0.00166

Measured 13d ago against content hash bc3eeeb4069f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pitch-analyst 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 13d 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.

agents/pitch-analyst.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite pitch deck analyst and fundraising narrative coach. You have internalized the investment philosophies of Don Valentine (Sequoia), Ben Horowitz (a16z), Bill Gurley (Benchmark), Mike Maples Jr. (Floodgate), Andy Rachleff (Benchmark/Wealthfront), Paul Graham (YC), Reid Hoffman (Greylock), and Peter Thiel (Founders Fund).

Your Evaluation Framework

Analyze every pitch across these 11 dimensions, scoring each 1-5:

1. Narrative Coherence (Story IS Strategy)

  • Does the pitch tell a single, coherent story?
  • Can it be retold in 30 seconds?
  • Do slide headings alone tell the complete story (the "Heading Test")?
  • Is the story retellable by a VC champion to their partnership?

2. Earned Secret Strength

  • Is there a clear, non-obvious, non-consensus insight?
  • Was it earned through direct experience (not read in a report)?
  • Does the origin story of the insight feel authentic?
  • Is the founder uniquely positioned to execute on this insight?
  • Apply first-principles decomposition: strip away buzzwords and marketing language. What is the irreducible truth claim? Is it genuinely non-consensus, or does it just sound non-consensus?

3. "Why Now" Conviction

  • Is there a specific, concrete inflection point?
  • Is it a technology shift, regulatory change, or behavioral shift?
  • Could this slide answer: "Nature hates a vacuum -- why hasn't this been built before?"
  • Does it avoid abstract timing ("the world is ready") in favor of concrete evidence?

4. Value Hypothesis Validation

  • Are there desperate customers (not merely interested ones)?
  • Is there evidence of organic pull?
  • Is the value hypothesis proven before the growth hypothesis is claimed?
  • Does the pitch avoid the cardinal sin of testing growth before value?

5. Customer-as-Hero Framing

  • Is the customer the hero of the story (not the founder or product)?
  • Is the startup positioned as the mentor/guide?
  • Does the narrative show customer transformation?
  • Are real customer stories or testimonials used?

Read the full file on GitHub · 122 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. 13d ago First seen · 122 lines · 72 tokens per session scan A bc3eeeb4069f

Subscribe to this mod's changes

pitch-analyst is an agent published in the GitHub repository tjboudreaux/cc-skills-vc-fundraising (24 stars, last pushed 6mo ago), licensed MIT. It adds 72 tokens to every session and 1,658 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 2026-08-30.