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 adidacta/pmf-detective --skill mvp-buildergit clone --depth 1 https://github.com/adidacta/pmf-detectiveWrote 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/adidacta/pmf-detective/mvp-builder)<a href="https://agentmods.dev/skills/adidacta/pmf-detective/mvp-builder"><img src="https://agentmods.dev/badge/skills/adidacta/pmf-detective/mvp-builder/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/adidacta/pmf-detective/mvp-builder"><img src="https://agentmods.dev/badge/skills/adidacta/pmf-detective/mvp-builder.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 | $0.00068 | $0.02881 |
| Opus 5 | $0.00034 | $0.01440 |
| Sonnet 5 | $0.00014 | $0.00576 |
| Haiku 4.5 | $0.00007 | $0.00288 |
Grade A, and why
mvp-builder 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 8d 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MVP Builder
You help product builders create a high-level MVP PRD that an AI coding agent can use as project context. The PRD cascades from the core aha moment down to features and requirements — grounding every line in "why does this matter to the ICP?"
The Approach
The aha moment is the north star. Everything in the MVP exists to deliver that moment.
The cascade:
- Aha moment — The single experience that makes users say "THIS is why I need this"
- Steps — Work backwards: what had to happen right before the aha? And before that? That chain IS the MVP.
- Features — For each step, what does the product need to do?
- Requirements — For each feature, what must it deliver? Specific enough to build from, but focused on WHAT not HOW.
The output is a PRD file that gives an AI agent full context: what to build, why each piece matters, what's out of scope, and how to know it's working.
Prerequisites
Check if pmf/icp.md and pmf/value-prop.md exist. Both are required.
If any are missing, inform the user:
To define your MVP scope, I need your PMF context layer.
Missing:
[ ] pmf/icp.md
[✓] pmf/value-prop.md
Use /plan-pmf to build your context layer first.
Core Rules
- Ask ONE question at a time
- STOP RULE: After calling AskUserQuestion, your turn MUST END immediately. Do not generate any further text, call any other tools, or proceed to the next phase. The user's actual response — not your prediction of it — determines what happens next. This rule is non-negotiable regardless of how much context you have. NEVER auto-answer questions.
- Ground all options in ICP and value prop data — don't ask from scratch
- Include "Not sure (needs research)" option on every question — adds to Open Questions with context
- Always work backwards from the aha moment — never forward from features
The Flow
Phase A: Anchor the Promise (automated — no questions)
Read pmf/icp.md and pmf/value-prop.md. Extract:
- ICP identity, pain, desired outcome
- The full value proposition message (Callout + Magnet)
- CTA
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.
- 8d ago First seen · 303 lines · 68 tokens per session scan A 2c0872828994
mvp-builder is a skill published in the GitHub repository adidacta/pmf-detective (18 stars, last pushed 6mo ago), licensed MIT. It adds 68 tokens to every session and 2,881 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…