Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ognjengt/founder-skillsnpx agentmods add skills/ognjengt/founder-skills/prd-generatorWrote 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/ognjengt/founder-skills/prd-generator)<a href="https://agentmods.dev/skills/ognjengt/founder-skills/prd-generator"><img src="https://agentmods.dev/badge/skills/ognjengt/founder-skills/prd-generator/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/ognjengt/founder-skills/prd-generator"><img src="https://agentmods.dev/badge/skills/ognjengt/founder-skills/prd-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 98 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 238 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00044 | $0.02137 |
| Opus 5 | $0.00022 | $0.01069 |
| Sonnet 5 | $0.00009 | $0.00427 |
| Haiku 4.5 | $0.00004 | $0.00214 |
Grade A, and why
prd-generator 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 10d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Generator
Purpose
Transform a rough product idea into a comprehensive, AI-ready Product Requirements Document (PDF) through targeted questions and structured output.
Execution Logic
Check $ARGUMENTS first to determine execution mode:
If $ARGUMENTS is empty or not provided:
Respond with: "prd-generator loaded, describe your product idea"
Then wait for the user to provide their product concept in the next message.
If $ARGUMENTS contains content:
Proceed immediately to Task Execution (skip the "loaded" message).
Task Execution
1. MANDATORY: Read Reference Files FIRST
BLOCKING REQUIREMENT — DO NOT SKIP THIS STEP
Before doing ANYTHING else, use the Read tool to read:
./references/prd_template.md
This template defines the exact structure your PRD must follow. DO NOT PROCEED to Step 2 until you have read this file.
2. Skip Business Context
This skill intentionally DOES NOT read FOUNDER_CONTEXT.md. PRDs are standalone documents that should contain all necessary context within them.
3. Analyze Initial Input
From the user's initial description, extract what's available:
- Product name or working title
- Core problem being solved
- Target users/audience
- Key features mentioned
- Technical preferences (if any)
- Constraints or requirements (if any)
4. Ask Clarifying Questions
Use AskUserQuestion tool to gather missing information. Ask up to 7 questions maximum, but fewer is better — stop as soon as you have enough to build a comprehensive PRD.
Question Bank (priority order):
| # | Question | Why it matters | Skip if... |
|---|---|---|---|
| 1 | Who is the primary user? What's their role and technical level? | Shapes all UX decisions and feature complexity | User persona is clearly described |
| 2 | What's the core problem this solves? What happens if users don't have this? | Defines the value proposition and success metrics | Problem statement is explicit |
| 3 | What are the 3-5 must-have features for launch (P0)? | Prevents scope creep, focuses MVP | Features are already listed with clear priority |
| 4 | What technology preferences or constraints exist? (Language, framework, hosting) | Determines technical architecture section | Tech stack is specified |
| 5 | Are there any integrations required? (Auth providers, APIs, third-party services) | Identifies dependencies and integration complexity | No external services mentioned or user says standalone |
| 6 | What does success look like? Any specific metrics to track? | Defines goals and success metrics section | Metrics or goals are already stated |
| 7 | Any design preferences or existing brand guidelines to follow? | Shapes UI/UX requirements section | Design is flexible or already described |
What ships with it
1 file 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.
- 10d ago First seen · 260 lines · 44 tokens per session scan A d33c1a7a2952
prd-generator is a skill published in the GitHub repository ognjengt/founder-skills (294 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 2,137 once invoked, about $0.0002 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.