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 gyanranjan/polyagent-skills --skill idea-to-mvpgit clone --depth 1 https://github.com/gyanranjan/polyagent-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/gyanranjan/polyagent-skills/idea-to-mvp)<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/idea-to-mvp"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/idea-to-mvp/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/gyanranjan/polyagent-skills/idea-to-mvp"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/idea-to-mvp.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 | $0.00149 | $0.03606 |
| Opus 5 | $0.00075 | $0.01803 |
| Sonnet 5 | $0.00030 | $0.00721 |
| Haiku 4.5 | $0.00015 | $0.00361 |
Grade A, and why
idea-to-mvp 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 11d 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea to MVP
Purpose
Transform a rough, informal idea (even a single paragraph) into a validated requirement document and actionable MVP plan. The agent acts as a domain-expert product manager — actively asking questions, confirming understanding, identifying skill gaps, researching the competitive landscape, and ultimately delivering a structured spec with mermaid diagrams ready for implementation handoff.
When to Use
- User provides a short idea or concept and wants to explore it
- User says "I have an idea", "help me figure out what to build"
- User wants to go from zero to a structured MVP plan
- User asks "what would the MVP look like for X?"
- User provides rough notes and wants a product manager perspective
When NOT to Use
- User already has formal requirements (use
requirement-studyinstead) - User has requirements and wants implementation tasks (use
implementation-sketch) - User wants to present an existing plan (use
deck-creator) - User wants to write code immediately (that's coding, not discovery)
Inputs
Required:
- Raw idea — a few lines of text describing what the user wants to build
Optional:
- Project name — if not provided, the agent will suggest one
- Target audience or market context
- Known technical constraints or preferences
- Budget or timeline context
- Existing competitors the user is already aware of
Process
Step 1: Preflight Tooling Check
Run non-blocking checks for tools needed later:
# Mermaid CLI for diagram rendering
if command -v mmdc >/dev/null 2>&1; then
mmdc --version
else
echo "mmdc not installed; diagrams will be inline Mermaid codeblocks"
fi
# PDF generation tooling (for final export)
if command -v pandoc >/dev/null 2>&1; then
echo "pandoc available"
else
echo "pandoc not installed; PDF export will need manual conversion"
fi
If tools are missing, note in agent.todo.md under Next but do not block.
Step 2: Capture and Summarize the Idea
Read the user's raw input carefully. Produce a 3-5 sentence summary that distills:
- What they want to build (the core product/feature)
- Who it is for (target users/audience)
- Why it matters (the problem being solved or value created)
What ships with it
2 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.
- 11d ago First seen · 362 lines · 149 tokens per session scan A 9d2ddf59a052
idea-to-mvp is a skill published in the GitHub repository gyanranjan/polyagent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 149 tokens to every session and 3,606 once invoked, about $0.0007 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
ti-founder
Founder profile template, creation questions, section definitions, and fit question guidance for TweakIdea evaluations.
ti-report
Jinja2 templates + CSS + data contract for TweakIdea evaluation reports.
brainstorming
You MUST use this before any creative work (features, products, content, strategy, systems, or behavior changes). Start by classifying what we’re brainstorming, then run thorough one-question-at-a-time discovery, propose 2–3 approaches, and converge on a validated plan/spec.
ti-hnparse
Python scripts for fetching a single HN post (hnparse.py) and searching HN posts via Algolia (hnsearch.py).
ti-scoring
TweakIdea 14-dimension startup evaluation framework with scoring rubrics and signal tables.
bilibili_search
Search for videos on Bilibili using keyword queries generated from user interests.