startup-problem-inventory

startup-problem-inventory is a skill for Claude Code from forjd/startup-ideation-skills. It costs 47 tokens per session (1,460 once invoked), scanned A, original, MIT.

A guided way to list startup problems before turning any of them into product ideas. It starts from the founder’s experience, customer access, workflows, complaints, and recent changes.

In plain words
What is it for?
Use it for an ideation sprint, exploring several industries, or turning personal experience into problem candidates. It can also produce a single HTML file containing the inventory.
Why use it?
It reduces the risk of jumping to polished ideas without first identifying a real, painful problem. It also helps compare which problems are worth investigating.

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 for an ideation sprint, exploring several industries, or turning personal experience into problem candidates. It can also produce a single HTML file containing the inventory.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/forjd/startup-ideation-skills/startup-problem-inventory
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-inventory
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-inventory

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/forjd/startup-ideation-skills/startup-problem-inventory"><img src="https://agentmods.dev/badge/skills/forjd/startup-ideation-skills/startup-problem-inventory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,460 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 $0.00047 $0.01460
Opus 5 $0.00023 $0.00730
Sonnet 5 $0.00009 $0.00292
Haiku 4.5 $0.00005 $0.00146

Measured 9d ago against content hash b92bef65b416, 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-inventory 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-inventory/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Startup Problem Inventory

When to use

Use when the user asks for startup ideas, wants to run an ideation sprint, has several domains to explore, or needs to turn founder experience into a list of problem candidates.

Do not produce a list of polished product ideas by default. First identify arenas where the founder has access, then collect raw problems and choose candidates worth putting into startup-problem-ledger.

Core rule

Treat a strong startup idea as a painful problem noticed from an unfair vantage point, made newly solvable by a change in technology, regulation, behaviour, cost, or distribution.

Use this mental model:

Strong candidate = painful problem + specific customer + founder insight + recent enabling change + cheap validation path + expansion option

Inputs to request if missing

Ask only the 3-5 questions that most affect the inventory:

Founder background:
Domains worked in:
Communities or customer groups reachable:
Tools, workflows, or industries personally suffered through:
Recent technology, regulation, or market changes noticed:
Ability to build or manually deliver a first solution:

If the user provides little context, still produce an inventory from stated experience and mark assumptions as Unknown.

Workflow

  1. Identify 3-5 idea arenas where the founder has unfair access.
  2. For each arena, list concrete workflows, recurring manual work, hated tools, compliance burdens, messy handoffs, spreadsheets, support complaints, or expensive services.
  3. Capture raw problem candidates without designing products.
  4. Screen each candidate for whether it is painful, specific, timely, underserved, founder-fit, and expandable.
  5. Prefer boring, specific, reachable problems over broad market narratives.
  6. Pick the best 3-5 candidates for startup-problem-ledger.
  7. Create an evidence packet seed for the top candidate.

Opportunity properties

Use these properties as a fast screen, not as false precision:

Read the full file on GitHub · 207 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 · 207 lines · 47 tokens per session scan A b92bef65b416

Subscribe to this mod's changes

startup-problem-inventory is a skill published in the GitHub repository forjd/startup-ideation-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,460 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.