A product-requirements workflow skill for defining a feature or new project before development starts. A PRD, or product requirements document, records the problem, users, scope, requirements, and acceptance conditions.

Use it to create a PRD, specify a feature, define a new project, or decide what needs to be settled before architecture and task planning.

It turns an unclear idea into an agreed description of what should be built and how success will be checked.

harness-prd — Skill for Claude Code and Codex by thaifurforo

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 thaifurforo/ai-toolkit --skill harness-prd

Clone the repo

git clone --depth 1 https://github.com/thaifurforo/ai-toolkit

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/thaifurforo/ai-toolkit/harness-prd/github.svg)](https://agentmods.dev/skills/thaifurforo/ai-toolkit/harness-prd)

Your own site

<a href="https://agentmods.dev/skills/thaifurforo/ai-toolkit/harness-prd"><img src="https://agentmods.dev/badge/skills/thaifurforo/ai-toolkit/harness-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/thaifurforo/ai-toolkit/harness-prd"><img src="https://agentmods.dev/badge/skills/thaifurforo/ai-toolkit/harness-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 640 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.

Model	Per session	Once invoked
Fable 5.1	$0.00074	$0.00640
Opus 5	$0.00037	$0.00320
Sonnet 5	$0.00015	$0.00128
Haiku 4.5	$0.00007	$0.00064

Measured 9d ago against content hash 149887da664c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

harness-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 9d 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/harness-prd/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness: PRD (Etapa 01)

Persona: ProductBuddy — facilitador interativo de PRDs.

Integrações

Verificar disponibilidade antes de usar (consultar harness.config.yaml). Se não disponível → usar harness-engineering/references/12-fallback-skills.md.

brainstorming (se disponível) — invocar antes se o escopo ainda está nebuloso; fallback: 12-fallback-skills.md § brainstorming
tlc-spec-driven (se disponível) — após o PRD, passar o documento ao TLC para iniciar o ciclo SPECIFY; fallback: continuar para harness-architecture

Quando Usar

Ativadores: "criar PRD", "especificar", "iniciar projeto", "o que definir antes de codar", "por onde começo"

NÃO usar esta skill: se o PRD já existe e você precisa de arquitetura → use harness-architecture

Processo

Construir o PRD de forma incremental, seção por seção, validando com o usuário antes de avançar.

Seções (em ordem):

Visão Geral — problema e por que resolver agora
Escopo — In / Out explícitos
Personas — quem usa, contexto real
Requisitos Funcionais — RF-01, RF-02… com critérios de aceite (CA-01…)
Requisitos Não Funcionais — RNF-01…
Fluxo de Usuário — jornada principal
Métricas de Sucesso — KPIs com baseline e meta
Riscos e Dependências
Anexos / Decisões adiadas

Ao final de cada seção: resumir → sugerir melhorias → perguntar "Posso registrar ou deseja ajustar?"

Se a resposta for vaga: oferecer 2–3 exemplos concretos e explicar por que a informação é essencial para as etapas seguintes.

Rastreabilidade por ID: RF-01 (PRD) → US-01 (story) → CA-01 (critério) → T-01 (task)

Saída Esperada

PRD completo em Markdown com IDs rastreáveis (RF-01, RNF-01, CA-01)
Persistido conforme project_tracking.tool em harness.config.yaml — ver harness-engineering/references/11-project-tracking.md

Próximo Passo → `harness-architecture`

Passe o PRD completo como contexto [PRD] para a etapa de arquitetura.

Template completo de prompt: Ver ./prompt.md

Read the full file on GitHub · 57 lines

Files

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.

prompt.md 3.5 KB

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.

9d ago First seen · 57 lines · 74 tokens per session scan A 149887da664c

Subscribe to this mod's changes

harness-prd is a skill published in the GitHub repository thaifurforo/ai-toolkit (5 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 640 once invoked, about $0.0004 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.

Planning Writing and docs

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

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens