expert-graham

expert-graham is a skill for Claude Code, Codex from AskRoundtable/expert-skills. It costs 36 tokens per session (2,337 once invoked), scanned A, original, MIT.

A module that applies Paul Graham’s ideas about startups, products, growth, and founder decisions. Paul Graham is a startup investor and essayist known for frameworks about finding problems, getting early users, and scaling carefully.

In plain words
What is it for?
Use it to evaluate startup ideas, validate products, decide what to build next, and think through early growth or hiring decisions.
Why use it?
It gives startup discussions a set of questions for testing whether an idea solves a real problem and whether growth reflects genuine demand.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to evaluate startup ideas, validate products, decide what to build next, and think through early growth or hiring decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/askroundtable/expert-skills/expert-graham
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 AskRoundtable/expert-skills --skill expert-graham
Clone the repo
git clone --depth 1 https://github.com/AskRoundtable/expert-skills

Made for: Claude Code, Codex.

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 expert-graham

README.md
[![agentmods](https://agentmods.dev/badge/skills/askroundtable/expert-skills/expert-graham.svg)](https://agentmods.dev/skills/askroundtable/expert-skills/expert-graham)
Your own site
<a href="https://agentmods.dev/skills/askroundtable/expert-skills/expert-graham"><img src="https://agentmods.dev/badge/skills/askroundtable/expert-skills/expert-graham.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,337 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 $0.00036 $0.02337
Opus 5 $0.00018 $0.01169
Sonnet 5 $0.00007 $0.00467
Haiku 4.5 $0.00004 $0.00234

Measured 8d ago against content hash a5053c474d22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

expert-graham 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 8d 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.

skills/expert-graham/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Expert Module: Paul Graham

Encodes Paul Graham's thinking patterns for use with expert-engine.

When to Load

Load this module when:

  • Evaluating startup ideas
  • Making early-stage growth decisions
  • Navigating founder challenges
  • Thinking about product-market fit
  • Deciding what to build next
  • Analyzing why startups succeed or fail

Problem Framing (What → Why):

What-layer questions that arrive here often:

  • "What startup idea should I work on?" → Why-layer: "What problem do you have unique insight into — and why hasn't anyone solved it yet?"
  • "How do I grow my startup faster?" → Why-layer: "Are you growing because you're making something people want, or because you're spending money?"
  • "When should I hire and scale up?" → Why-layer: "Are you Default Alive or Default Dead — and does adding headcount change that math?"

When the user presents a What question, ask:

"Does this idea pass the Tarpit test — if it's so obviously good, why hasn't someone already done it? And are you willing to Do Things That Don't Scale to get your first ten users who truly love it?"

Domain Boundaries

Core Domain (High Confidence): Paul Graham's frameworks work best for early-stage startups, idea generation, and founder decisions. Use with full confidence.

  • Startup idea validation
  • Early-stage growth strategy
  • Founder psychology and motivation
  • Product development priorities
  • Fundraising timing and strategy

Extended Domain (Moderate Confidence): The mental models (Do Things That Don't Scale, Schlep Blindness, etc.) apply more broadly. Use the frameworks, but acknowledge they were designed for startups.

  • Career decisions about building vs. joining
  • Creative project prioritization
  • Writing and communication clarity
  • General decision-making about ambition

Outside Domain (Low Confidence): For these areas, acknowledge limitations upfront. Provide general thinking frameworks only.

  • Late-stage company strategy
  • Enterprise sales and operations
  • Non-tech industries
  • Established business optimization

Read the full file on GitHub · 265 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 265 lines · 36 tokens per session scan A a5053c474d22

Subscribe to this mod's changes

expert-graham is a skill published in the GitHub repository AskRoundtable/expert-skills (51 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 2,337 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

thinking-partner

A deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, solve problems, and think more clearly. Use this skill whenever a user says "help me think through X", "challenge my thinking", "what am I missing", "apply mental models to this", "play devil's advocate"…

mattnowdev/thinking-partner · 183 tokens

thinking-toolkit

A toolkit of 30 decision-making, problem-solving, systems-thinking, and communication models, plus a /logic mode that audits an argument's validity. This skill should be used when a user names a specific model, or describes a situation that calls for one: framing or reframing a problem, comparing options, setting…

ponomr/thinking-toolkit · 140 tokens

blindspot-check

Checks a big decision for blind spots against a catalogue of 95 cognitive biases before the user commits. Use when the user is about to make or has just justified a major life decision and wants to be checked for self-deception — buying a house, relocating, signing a long lease or contract, quitting or taking a job…

soheilmomeniii/blindspot-check · 219 tokens

council

Evidence-bound multi-agent council for high-stakes decisions. Scout uses last30days, Advocate and Skeptic debate, Fact Checker uses deep-research Quick mode. Delivers ranked options with #1 marked, dissent preserved, and the condition that would flip the verdict. Use when user says council this, /council, run the…

Endokelp/DecisionCouncil · 124 tokens

munger-mental-models

A structured decision-analysis toolkit based on Charlie Munger's mental models from multiple academic disciplines.

Angrycain/munger-mental-models · 1,169 tokens

reflect

Think through any decision — code, business, personal — and get a straight answer. Fires on "reflect on X", "start from first principles", "reflect"; AND fire it YOURSELF, unprompted, whenever the work hits a choice whose undo cost exceeds a bad day (architecture, dependencies, pricing, public commitments, people) or…

seldonframe/reflect · 112 tokens