prd

prd is a skill for Claude Code, Codex from 0xrafasec/ai-workflow. It costs 66 tokens per session (1,038 once invoked), scanned A, original, MIT.

An interview-driven document for describing a product's requirements, including users, user stories, scope, and measures of success. It is commonly called a Product Requirements Document, or PRD.

In plain words
What is it for?
Use it when deciding what to build, defining the first release, recording exclusions, identifying stakeholders, or setting success criteria.
Why use it?
It turns an early product idea into shared written decisions and checks existing project documents first to avoid duplicating or overlooking them.

Skill for Claude CodeCodex

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/0xrafasec/ai-workflow/prd
Any agent
npx skills add 0xrafasec/ai-workflow --skill prd
Clone the repo
git clone --depth 1 https://github.com/0xrafasec/ai-workflow

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 prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/0xrafasec/ai-workflow/prd.svg)](https://agentmods.dev/skills/0xrafasec/ai-workflow/prd)
Your own site
<a href="https://agentmods.dev/skills/0xrafasec/ai-workflow/prd"><img src="https://agentmods.dev/badge/skills/0xrafasec/ai-workflow/prd.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,038 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 $0.00066 $0.01038
Opus 5 $0.00033 $0.00519
Sonnet 5 $0.00013 $0.00208
Haiku 4.5 $0.00007 $0.00104

Measured 4d ago against content hash cb9eb4a121a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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/prd/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a Product Requirements Document for: $ARGUMENTS

Context Awareness

Before starting, check what already exists:

  • Read docs/ directory structure if it exists
  • Read any existing PRD, README, or whitepaper — do not duplicate what's already written
  • If a PRD already exists, ask the user if they want to revise it or start fresh

Process

1. Deep Interview

Use AskUserQuestion to interview the user. This is the most important step — the PRD quality depends entirely on how well you extract the user's thinking.

Start broad, then go deep:

  1. The problem — What problem are you solving? Who has this problem? How are they solving it today? What's broken about the current approach?
  2. The solution — What's your high-level approach? What makes it different from existing solutions? What's the core insight?
  3. Scope and boundaries — What does v1 include? What is explicitly out of scope? What are the non-negotiable requirements vs nice-to-haves?
  4. Users and stakeholders — Who are the primary users? Are there different user types with different needs? Who else cares about this (ops, security, compliance)?
  5. Success criteria — How do you know this works? What does success look like in 1 month? 6 months?
  6. Constraints — Technical constraints (language, platform, infra)? Business constraints (timeline, team size, budget)? Regulatory constraints?
  7. Risks — What could go wrong? What are the biggest unknowns? What keeps you up at night about this?

Interview rules:

  • Don't ask obvious questions — if the user said "Rust CLI tool", don't ask "what language?"
  • Dig into contradictions and tensions — "you said X but also Y, how do those reconcile?"
  • Ask about the hard parts the user might not have thought through
  • It's OK to push back or challenge assumptions — the goal is a solid PRD, not agreement
  • Keep going until you have enough to write a comprehensive document. Don't rush.

2. Write the PRD

Write to docs/PRD.md (or docs/prd/<name>.md if this is a sub-feature PRD).

Read the full file on GitHub · 112 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. 4d ago First seen · 112 lines · 66 tokens per session scan A cb9eb4a121a9

Subscribe to this mod's changes

prd is a skill published in the GitHub repository 0xrafasec/ai-workflow (9 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,038 once invoked, about $0.0003 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

ideate

Clarifies a rough idea into a precise problem specification through structured dialogue. Asks targeted questions to surface assumptions, scope, constraints, and actors. Produces a specification document defining WHAT needs to change — not HOW to change it. Use when starting a new feature, brainstorming an idea…

mock-server/mockserver-monorepo · 107 tokens

simple-english

Write or rewrite text in plain, layman-readable English in the spirit of ASD-STE100 Simplified Technical English: short sentences, active voice, simple tenses, one word one meaning, condition before command, every technical term defined at first use, no AI slop. Default mode is Plain. Strict mode applies full STE…

AminBlg/SimpleEnglish · 212 tokens

prd

Generates a Product Requirements Document from a natural language app description. Asks clarifying questions, researches similar apps, defines scope, stack, architecture, and produces a structured PRD that Archon can decompose into a campaign.

SethGammon/Citadel · 48 tokens

dbt-docs

Document dbt models and columns in schema.yml with business context — model descriptions, column definitions, and doc blocks. Use when adding or improving documentation for discoverability. Powered by altimate-dbt.

AltimateAI/altimate-code · 45 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

35-brand-voice-global

Use when the user needs to define, document, or enforce how the brand SOUNDS in writing — three personality traits, a five-dimension tone table, vocabulary to use, avoid, and ban, sentence rules, before and after rewrites, platform adaptation, and a copy approval checklist. Every content skill reads it before writing.…

minhnv0807/ai-business-skills · 163 tokens