startup-problem-grilling

startup-problem-grilling is a skill for Claude Code from forjd/startup-ideation-skills. It costs 31 tokens per session (2,091 once invoked), scanned A, original, MIT.

A structured way to challenge a startup idea by asking direct questions about the problem, buyer, urgency, evidence, and ability to reach customers. It is used before validation work or deciding what to build.

In plain words
What is it for?
Use it to examine a problem ledger, test whether a business idea is worth pursuing, identify the most important unanswered questions, and assess distribution, alternatives, founder fit, and the scope of a first version.
Why use it?
It exposes weak assumptions early, such as a problem that is not urgent, a buyer who will not pay, or a product that is too broad to build and sell quickly.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the startup-ideation-skills plugin — 6 skills shipped together

Good fit Use it to examine a problem ledger, test whether a business idea is worth pursuing, identify the most important unanswered questions, and assess distribution, alternatives, founder fit, and the scope of a first version.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/forjd/startup-ideation-skills/startup-problem-grilling
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 forjd/startup-ideation-skills --skill startup-problem-grilling
Clone the repo
git clone --depth 1 https://github.com/forjd/startup-ideation-skills

Made for: Claude Code.

Or install startup-ideation-skills, the plugin that ships this one along with the rest of its 6 skills.

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 startup-problem-grilling

README.md
[![agentmods](https://agentmods.dev/badge/skills/forjd/startup-ideation-skills/startup-problem-grilling/github.svg)](https://agentmods.dev/skills/forjd/startup-ideation-skills/startup-problem-grilling)
Your own site
<a href="https://agentmods.dev/skills/forjd/startup-ideation-skills/startup-problem-grilling"><img src="https://agentmods.dev/badge/skills/forjd/startup-ideation-skills/startup-problem-grilling/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 startup-problem-grilling

Your own site · 80×15
<a href="https://agentmods.dev/skills/forjd/startup-ideation-skills/startup-problem-grilling"><img src="https://agentmods.dev/badge/skills/forjd/startup-ideation-skills/startup-problem-grilling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,091 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 $0.00031 $0.02091
Opus 5 $0.00015 $0.01045
Sonnet 5 $0.00006 $0.00418
Haiku 4.5 $0.00003 $0.00209

Measured 9d ago against content hash c26d13036aee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

startup-problem-grilling 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 9d 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/startup-problem-grilling/SKILL.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Startup Problem Grilling

When to use

Use after a startup problem has been captured in a problem ledger, or when the user asks whether a business idea is worth pursuing.

This skill is deliberately sceptical. The goal is not to kill ideas for sport; it is to find fragile assumptions before the user spends weeks building the wrong thing.

Stance

Be direct, practical, and specific. Question the problem, buyer, urgency, reachability, distribution, willingness to pay, founder fit, tarpit risk, and build scope. Avoid generic startup theatre.

Inputs to request if missing

Use the evidence packet or problem ledger if it is already in context. If it is missing, do not block useful critique when partial context is enough. Ask only the 3–5 missing questions that would most change the verdict.

Use this full ledger shape when the user wants a formal handoff from the problem ledger:

Problem:
User/persona:
When it happens:
Current workaround:
Cost of doing nothing:
Frequency:
Potential buyer:
Existing tools/alternatives:
Why now:
Founder advantage:
Distribution route:
Expansion path:
Could I reach 10 users:
Could I build v1 in 2–4 weeks:

Grilling workflow

  1. Restate the problem in its strongest concrete form.
  2. Identify the weakest 3–5 assumptions.
  3. Map user, buyer, blocker, budget owner, and risk owner.
  4. Check tarpit risk and whether distribution may be harder than product.
  5. Challenge pricing and willingness-to-pay early.
  6. Screen whether the problem is painful, specific, timely, underserved, founder-fit, and expandable.
  7. Score founder-market fit against the user's actual advantages.
  8. Suggest small validation moves that do not require building the full product.
  9. End with a verdict: Promising, Needs narrowing, Weak until proven, or Probably not worth building yet.
  10. Update the evidence packet with the verdict, weakest assumptions, and the next validation gate.

Question bank

Problem reality

  • Is this painful enough that people already spend time, money, or political capital on it?
  • What happens if they ignore it?
  • Is it a frequent problem, a severe problem, or neither?
  • Is the pain felt by the same person who would approve a fix?
  • Is the current workaround hated, or merely untidy?

Read the full file on GitHub · 310 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. 9d ago First seen · 310 lines · 31 tokens per session scan A c26d13036aee

Subscribe to this mod's changes

startup-problem-grilling is a skill published in the GitHub repository forjd/startup-ideation-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 2,091 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 2026-08-31.