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.
npx skills add heyparsadev/claude-idea-validator --skill idea-stagegit clone --depth 1 https://github.com/heyparsadev/claude-idea-validatorWrote 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.
[](https://agentmods.dev/skills/heyparsadev/claude-idea-validator/idea-stage)<a href="https://agentmods.dev/skills/heyparsadev/claude-idea-validator/idea-stage"><img src="https://agentmods.dev/badge/skills/heyparsadev/claude-idea-validator/idea-stage/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.
<a href="https://agentmods.dev/skills/heyparsadev/claude-idea-validator/idea-stage"><img src="https://agentmods.dev/badge/skills/heyparsadev/claude-idea-validator/idea-stage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00228 | $0.02575 |
| Opus 5 | $0.00114 | $0.01288 |
| Sonnet 5 | $0.00046 | $0.00515 |
| Haiku 4.5 | $0.00023 | $0.00258 |
Grade C, and why
idea-stage scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
description: This skill should be used when a founder wants to validate, pressure-test, or kill a startup/product idea before building it — sharpening a hunch into a testable hypothesis, red-teaming it, sizing the market How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Stage — validate before you build
Implements Chapter 3 of The Founder's Playbook: Building an AI-Native Startup (Anthropic, 2026).
The entire stage answers one question: is this worth building? It ends at problem–solution fit — qualitative evidence, primarily from real human conversations, that a real problem exists for real people and that the proposed solution addresses the problem discovery revealed, not the one originally assumed.
The book's core warning drives every rule below: agentic coding collapsed the distance between "I have an idea" and "I have a product," and AI research gave confirmation bias an engine. 42% of startups failed by building something nobody wanted — before AI made building nearly free. This skill exists to keep sense-making ahead of building.
Prime directives — never violate these
- Evidence is graded; grade D never passes a gate. Every claim entering the workspace gets a grade (A/B/C/D) and a source. See
references/evidence-ledger.md. An exit criterion answered only by AI reasoning is not answered. - Never invent a user, a quote, an interview, or a number. Simulated personas may be used to rehearse interviews; they are labelled
[SIMULATED], graded D, and can never satisfy a gate. If a figure cannot be sourced, writeno data found. - A prototype is a conversation prop, never evidence. Its existence proves nothing about demand. Reactions from real humans holding it are the evidence.
- Disconfirming evidence gets equal airtime. Every research step must produce both the case for and the case against, and the case against is written first.
- No production code in this stage. The only build allowed is the single-interaction throwaway prototype at step 9. If the founder wants to start building sooner, say so plainly and point at the gate.
- Kill criteria are written before research starts, not after (step 0). Falsifiability first, or the whole exercise becomes theater.
Language
What ships with it
6 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.
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.
- 9d ago First seen · 120 lines · 228 tokens per session scan C 9224ee29b66f
idea-stage is a skill published in the GitHub repository heyparsadev/claude-idea-validator (2 stars, last pushed 28d ago), licensed MIT. It adds 228 tokens to every session and 2,575 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
first-customer-finder
Find and qualify evidence-backed potential first customers, early adopters, design partners, or beta users for a startup using recent public pain and buying signals. Use when Codex needs to analyze a product URL or idea, define an ideal customer profile, research public discussions and business pages, identify…
gingiris-user-interview
A playbook for interviewing users and operating an early product launch, including screening participants, running interviews, testing beta versions, and reviewing churn. It is based on a described process for finding product-market fit, meaning a product consistently meeting a real user need.
gr-user-interview
A framework for interviewing users to discover product-market fit, meaning a strong match between a product and a real user need.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
review
5-pass structured code review — correctness, security, performance, readability, consistency.