agentmods.dev

to-prd

to-prd is a skill for Claude Code from murilomn58/Claude-Spec-Driven-Fase-Zero. It costs 130 tokens per session (1,611 once invoked), scanned A, original, MIT.

A requirements document that turns an agreed project brief and codebase understanding into a clear plan. It includes user stories, architecture decisions, and test decisions.

In plain words
What is it for?
Use it after requirements have been discussed to write a product requirements document (PRD), define expected user outcomes, and record how the software should be structured and tested.
Why use it?
It prevents important decisions from being lost or left vague before implementation begins. It also gives later issue planning and coding a shared reference.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the adp-fase-zero plugin — 2 skills shipped together

not rated 1repo 2mo ago A scan 130 tokens original MIT

Good fit Use it after requirements have been discussed to write a product requirements document (PRD), define expected user outcomes, and record how the software should be structured and tested.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/murilomn58/claude-spec-driven-fase-zero/to-prd
View source ↗ murilomn58/Claude-Spec-Driven-Fase-Zero claudespecdriven.com.br
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.

Any agent
npx skills add murilomn58/Claude-Spec-Driven-Fase-Zero --skill to-prd
Clone the repo
git clone --depth 1 https://github.com/murilomn58/Claude-Spec-Driven-Fase-Zero

Made for: Claude Code.

Or install adp-fase-zero, the plugin that ships this one along with the rest of its 2 skills.

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 to-prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/murilomn58/claude-spec-driven-fase-zero/to-prd/github.svg)](https://agentmods.dev/skills/murilomn58/claude-spec-driven-fase-zero/to-prd)
Your own site
<a href="https://agentmods.dev/skills/murilomn58/claude-spec-driven-fase-zero/to-prd"><img src="https://agentmods.dev/badge/skills/murilomn58/claude-spec-driven-fase-zero/to-prd/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.

agentmods 80×15 button for to-prd

Your own site · 80×15
<a href="https://agentmods.dev/skills/murilomn58/claude-spec-driven-fase-zero/to-prd"><img src="https://agentmods.dev/badge/skills/murilomn58/claude-spec-driven-fase-zero/to-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,611 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00130 $0.01611
Opus 5 $0.00065 $0.00805
Sonnet 5 $0.00026 $0.00322
Haiku 4.5 $0.00013 $0.00161

Measured 10d ago against content hash fe5c76d3678b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

to-prd 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.

skills/to-prd/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

to-prd

Fase 1 do ADP (Especificar). Pega o brief afiado da grill-me e o entendimento do codebase e produz um PRD claro: o contrato que o to-issues fatia e o tech-lead executa. Reescrita da to-prd do Matt Pocock, adaptada ao ADP.

SUB-SKILLS RECOMENDADAS (opcionais — sem elas, siga o processo descrito nesta própria skill): superpowers:writing-plans (use o RIGOR e o zero-ambiguidade dele, NAO o seu formato-com-paths: o nivel de detalhe aqui e o da secao "Nivel de detalhe" abaixo) + feature-dev:code-architect (blueprint arquitetural: quais modulos criar/mudar, interfaces, fluxo de dados, sequencia). Esta skill orquestra os dois no formato PRD do ADP.

Input

O brief afiado em docs/adp/<slug>-brief.md (saida da grill-me). Se ele nao existir, rode a grill-me antes: nao pule a Fase 0. O PRD sintetiza o brief, nao o substitui.

Regra de ouro: sintetizar, nao re-entrevistar

A grill-me ja grelhou você. Aqui e sintese do que ja foi decidido, nao uma nova rodada de perguntas. Se ao escrever aparecer um buraco REAL (uma decisao que nunca foi tomada), volte pontualmente a grelhar so aquele ponto, nao refaca a descoberta inteira.

Processo

  1. Ancorar no codebase. Despache o feature-dev:code-architect para mapear o estado real e desenhar onde a feature encaixa. Se ele nao se aplicar ou falhar (projeto estatico/estrutura atipica), NAO re-tente igual: mapeie via subagente Explore com Glob/Read (caminho absoluto) e siga. Use o glossario e as decisoes do brief. Respeite as convencoes backend-layers / frontend-react (ou a variante vanilla-static) e ADRs da area tocada.
  2. Definir os seams (costuras de teste). Onde a feature sera testada? Prefira seams existentes; use o seam mais ALTO possivel; minimize o numero (o ideal e um). Confirme com o usuário que os seams batem com a expectativa. Isso ja prepara a Fase 4 (QA) e evita teste acoplado a implementacao.
  3. Escrever o PRD com o template abaixo, em docs/adp/<slug>-prd.md.
  4. Gate humano (PRD).

Read the full file on GitHub · 62 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. 10d ago First seen · 62 lines · 130 tokens per session scan A fe5c76d3678b

Subscribe to this mod's changes

to-prd is a skill published in the GitHub repository murilomn58/Claude-Spec-Driven-Fase-Zero (1 stars, last pushed 2mo ago), licensed MIT. It adds 130 tokens to every session and 1,611 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.

Claude CodePlanningai-codinganthropicclaudeclaude-code-plugindeveloper-tools
Related

Other skills, from other repositories

justone

Runtime contract for the Just One Prompt Challenge. Invoked exclusively via the /justone and /justone-publish slash commands. Do NOT auto-trigger from general conversation — only act on this skill when one of those commands has been issued in the current turn.

GodsB1025/justone · 55 tokens

memstack-security-owasp-top10

Use this skill when the user says 'OWASP audit', 'OWASP top 10', 'security audit', 'vulnerability assessment', 'full security check', or needs a comprehensive web application security review against OWASP Top 10 categories. Do NOT use for dependency audits or secret scanning alone.

cwinvestments/memstack · 69 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

memstack-business-scope-of-work

Use this skill when the user says 'scope of work', 'SOW', 'define scope', 'project scope', 'write SOW', 'scope document', or is defining project boundaries, deliverables, and acceptance criteria for a formal engagement. Do NOT use for proposals, contracts, or invoicing.

cwinvestments/memstack · 70 tokens

memstack-content-youtube-script

Use this skill when the user says 'YouTube script', 'video script', 'write script for YouTube', 'YouTube video outline', or is creating scripted content for a YouTube video with hooks, chapters, and CTAs. Do NOT use for TikTok/Reels short-form scripts or webinar presentations.

cwinvestments/memstack · 70 tokens

memstack-seo-local-seo

Use this skill when the user says 'local SEO', 'Google Business Profile', 'local search', 'NAP consistency', 'local listings', 'Google Maps', 'local pack', or is optimizing a business for local search results and map visibility. Do NOT use for general SEO audits or national keyword research.

cwinvestments/memstack · 69 tokens