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 MartinOlivero/saas-builder --skill product-discoverygit clone --depth 1 https://github.com/MartinOlivero/saas-builderWrote 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/martinolivero/saas-builder/product-discovery)<a href="https://agentmods.dev/skills/martinolivero/saas-builder/product-discovery"><img src="https://agentmods.dev/badge/skills/martinolivero/saas-builder/product-discovery/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/martinolivero/saas-builder/product-discovery"><img src="https://agentmods.dev/badge/skills/martinolivero/saas-builder/product-discovery.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 | $0.00113 | $0.00637 |
| Opus 5 | $0.00056 | $0.00318 |
| Sonnet 5 | $0.00023 | $0.00127 |
| Haiku 4.5 | $0.00011 | $0.00064 |
Grade A, and why
product-discovery 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Discovery
This skill turns a fuzzy idea into a sharp, buildable MVP. It is inspired by Design Sprint and Lean Startup, and it resists the urge to jump to features before the problem is understood.
Analogy: do not prescribe medicine before diagnosing the illness. Most failed products are perfectly built cures for a disease nobody has.
Workflow
PHASE 1 — Understand the problem (not the solution)
Force the conversation onto the problem first. Ask:
- What specific problem are you solving?
- Who has that problem? Describe that person concretely.
- How do they solve it today? (even if it is Excel, WhatsApp, or by hand)
- Why is that current solution not good enough?
Do not let the discussion drift to features yet. If the user describes a solution, redirect to the problem it serves.
PHASE 2 — Validate the market
- Do you (or your target users) already pay for something similar? How much?
- Do you know other people with this same problem?
- Do you have access to potential customers to validate with?
The goal is evidence that the problem is real and painful enough that someone will pay.
PHASE 3 — Define the MVP
- What is the minimum result that would make someone pay?
- Which features are "nice to have" but not essential?
- How soon do you want something to show?
The MVP is the smallest thing that delivers the core result — not a small version of the full vision.
PHASE 4 — Output
Deliver these five items:
- Problem definition — in one sentence.
- Ideal customer avatar — who they are, concretely.
- MVP scope — a prioritized feature list:
- P0 — must exist for the MVP to deliver its core result.
- P1 — important, but can wait for v1.1.
- P2 — nice to have; explicitly deferred.
- Success metric — how we will know it worked (e.g. "10 paying users in 30 days," "40% of signups complete the core action").
- Concrete next step — the single next action to take.
Handoff
Once the MVP is defined, hand off to architecture-primer to decide how to build it, then ui-design to build the interface. Discovery answers (scale expectations, user type, timeline) feed directly into the architecture discovery phase — pass them along.
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 · 57 lines · 113 tokens per session scan A 7ba8156cdee0
product-discovery is a skill published in the GitHub repository MartinOlivero/saas-builder (2 stars, last pushed 24d ago), licensed MIT. It adds 113 tokens to every session and 637 once invoked, about $0.0006 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
architecture-paradigm-microkernel
Applies microkernel architecture with minimal core and plugin extensibility. Use when building platforms where third parties extend core functionality.
plan
Use when a task needs structured planning before implementation. Supports --delegate and round=N[,M].
preplan
Use when a problem needs clarification and agreement before planning begins. Supports --deep and --delegate.
ralph
Use when implementing a plan or executing a prompt that requires verified completion.
pathfind
Use when you have problems but don't know what to build.
analyze
Use when deep investigation is needed — project structure, requirement gaps, or root cause diagnosis. Supports --delegate.