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 Hades-HY-LI/ai-native-founder-playbook-skills --skill ai-native-idea-stagegit clone --depth 1 https://github.com/Hades-HY-LI/ai-native-founder-playbook-skillsWrote 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/hades-hy-li/ai-native-founder-playbook-skills/ai-native-idea-stage)<a href="https://agentmods.dev/skills/hades-hy-li/ai-native-founder-playbook-skills/ai-native-idea-stage"><img src="https://agentmods.dev/badge/skills/hades-hy-li/ai-native-founder-playbook-skills/ai-native-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/hades-hy-li/ai-native-founder-playbook-skills/ai-native-idea-stage"><img src="https://agentmods.dev/badge/skills/hades-hy-li/ai-native-founder-playbook-skills/ai-native-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 | $0.00060 | $0.00653 |
| Opus 5 | $0.00030 | $0.00327 |
| Sonnet 5 | $0.00012 | $0.00131 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
ai-native-idea-stage 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Native Idea Stage
Goal
Help founders determine whether a problem is real, urgent, reachable, and especially suited to AI-native execution before investing in an MVP.
Required Inputs
If the founder provides a structured brief, use these inputs:
Target customer:
Problem hypothesis:
Existing alternatives:
Why now:
Current evidence:
Founder advantage:
Biggest uncertainty:
Desired output:
Guided Intake
Do not require the founder to know all details upfront. If the request is vague, ask up to five questions first:
1. Who do you think has this problem?
2. What painful workflow, cost, or delay are you trying to fix?
3. How do they solve it today?
4. What evidence do you have so far: conversations, observations, data, or none?
5. What do you want next: interview plan, opportunity scorecard, wedge, or MVP proof target?
After the user answers, identify assumptions, fill unknowns as unknown, and produce the requested recommendation. Ask follow-up questions only when a missing answer would materially change the recommendation.
Workflow
- Restate the hypothesis as customer, problem, trigger, current workaround, and promised outcome.
- Identify the riskiest assumptions: pain severity, budget or urgency, access to customers, AI feasibility, differentiation, and wedge.
- Use
references/customer-discovery.mdwhen the user needs interviews, survey prompts, or research synthesis. - Use
references/opportunity-filter.mdwhen comparing ideas or deciding whether to continue. - Use
references/ai-native-wedge.mdwhen the user needs a focused first market or AI-native differentiation. - Produce a concrete evidence plan with actions the founder can run in days, not months.
AI-Native Workflows
Use generic AI roles, not vendor-specific products:
- Research assistant: summarize markets, alternatives, and customer language.
- Interview copilot: draft questions, analyze transcripts, and identify repeated pains.
- Strategy critic: pressure-test assumptions and expose weak claims.
- Prototype explainer: sketch low-fidelity concepts before engineering starts.
What ships with it
4 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.
- 12d ago First seen · 86 lines · 60 tokens per session scan A 72160f43f129
ai-native-idea-stage is a skill published in the GitHub repository Hades-HY-LI/ai-native-founder-playbook-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 653 once invoked, about $0.0003 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.
Other skills, from other repositories
tastemaker
Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…
fde
Keeps the engagement record for client work. Use when they name a client or stakeholder. Use when they debrief a meeting or paste notes. Use when they ask what was agreed. Use when they run a POC, change the client's codebase, prove it on their staging, go live, or need evals before a model acts. Use when they prep a…
kubernetes-skill
Prevent Kubernetes hallucinations by diagnosing and fixing failure modes: insecure workload defaults, resource starvation, network exposure, privilege sprawl, fragile rollouts, and API drift. Use when generating, reviewing, refactoring, or migrating manifests, Helm charts, Kustomize overlays, cluster policies, and…
image-to-psd
A skill that reconstructs images as editable, layered Photoshop files. It separates the repaired background, visual components, and text into layers instead of leaving the page as one flat image.
img2mo-learn
Learn reusable 2D motion-generation knowledge from user-specified action resources with /img2mo-learn . Use when the user provides videos, extracted frame sequences, spritesheets, Spine assets, generated outputs, failed attempts, or reference motion folders and wants to summarize animation timing, pose beats, style…
img2mo-std
Standardize a 2D animation baseline image with /img2mo-std xxx.png/pos. Use when preparing a character, creature, prop, or weapon baseline before motion generation, especially if the source image is too large, tightly cropped, lacks transparent action margin, has a white background, or later walk/attack/idle frames…