generator

generator is a skill for Claude Code, Codex from mrtblount/Spec-to-Ship. It costs 35 tokens per session (962 once invoked), scanned A, original, MIT.

A document-building step that turns product discovery and market research into a Product Requirements Document, or PRD—a plan describing what a product should do and why.

In plain words
What is it for?
Use it to create a PRD from discovery notes, research notes, and a provided template, including priorities and only relevant sections.
Why use it?
It brings scattered notes and research into one specific, prioritized document. It also keeps the problem separate from the proposed solution.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

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.

agentmods
npx agentmods add skills/mrtblount/spec-to-ship/generator
Any agent
npx skills add mrtblount/Spec-to-Ship --skill generator
Clone the repo
git clone --depth 1 https://github.com/mrtblount/Spec-to-Ship

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrtblount/spec-to-ship/generator.svg)](https://agentmods.dev/skills/mrtblount/spec-to-ship/generator)
Your own site
<a href="https://agentmods.dev/skills/mrtblount/spec-to-ship/generator"><img src="https://agentmods.dev/badge/skills/mrtblount/spec-to-ship/generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 962 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00962
Opus 5 $0.00017 $0.00481
Sonnet 5 $0.00007 $0.00192
Haiku 4.5 $0.00003 $0.00096

Measured 5d ago against content hash 73f5a2b9b94c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 5d 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.

prd-builder/sub-skills/generator/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write in plain English. Be specific. Be concise. Every sentence should either define what the product does or inform a decision.

Inputs

READ both:

  • _prd/discovery-notes.md — user's vision, problem, features, context
  • _prd/research-notes.md — market context, competitors, user patterns

Also READ the PRD template at:

  • references/prd-template.md — the output structure to follow

Generation Rules

  1. Use the user's language. If they called it "smart suggestions," don't rename it to "AI-powered recommendation engine" in the PRD.

  2. Be ruthlessly specific. "Good UX" is useless. "Onboarding completes in under 60 seconds with zero configuration" is useful.

  3. Separate problem from solution. The problem statement should make sense even if you removed every feature. The features should clearly trace back to the problem.

  4. Include only what applies. If the product doesn't use AI, omit the AI sections entirely. If there's no compliance concern, don't add a compliance section for the sake of completeness.

  5. Prioritize clearly. Every feature should be tagged as Must-Have, Nice-to-Have, or Future. If the user didn't prioritize, use the "would we delay launch for this?" test.

  6. Ground in research. Reference competitive gaps, user patterns, and market context where they strengthen the rationale for decisions.

  7. Flag open questions. Don't paper over uncertainty. If the user said "I don't know" during discovery, it goes in the Open Questions section.

  8. Write user stories for real humans. Not "As a user, I want to log in so that I can access the app." Write stories that capture actual user motivation and context.

Read the full file on GitHub · 114 lines

Changes

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.

  1. 5d ago First seen · 114 lines · 35 tokens per session scan A 73f5a2b9b94c

Subscribe to this mod's changes

generator is a skill published in the GitHub repository mrtblount/Spec-to-Ship (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 962 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 95 tokens