prd-first

prd-first is a skill for Claude Code from Abhillashjadhav/AI-PM-essential-skills. It costs 199 tokens per session (1,881 once invoked), scanned A, original, MIT.

A planning rule that requires a written product requirements document before generating code. A product requirements document records the problem, users, and intended behavior of an app.

In plain words
What is it for?
Guiding idea-to-code work through a series of questions, then storing the result as a dated Markdown document in the project. It applies to requests such as building, prototyping, or shipping an app.
Why use it?
It turns a vague app idea into a written agreement before implementation starts. This helps prevent generated code from drifting away from the original purpose.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

Good fit Guiding idea-to-code work through a series of questions, then storing the result as a dated Markdown document in the project. It applies to requests such as building, prototyping, or shipping an app.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/abhillashjadhav/ai-pm-essential-skills/prd-first
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 Abhillashjadhav/AI-PM-essential-skills --skill prd-first
Clone the repo
git clone --depth 1 https://github.com/Abhillashjadhav/AI-PM-essential-skills

Made for: Claude Code.

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-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/prd-first/github.svg)](https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/prd-first)
Your own site
<a href="https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/prd-first"><img src="https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/prd-first/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 prd-first

Your own site · 80×15
<a href="https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/prd-first"><img src="https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/prd-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 199 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,881 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 $0.00199 $0.01881
Opus 5 $0.00100 $0.00941
Sonnet 5 $0.00040 $0.00376
Haiku 4.5 $0.00020 $0.00188

Measured 11d ago against content hash 7269381df03f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prd-first 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 11d 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.

.claude/skills/prd-first/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD-First Discipline

The user (Abhillash) vibe-codes 10-15 apps and loses track of what each app is actually doing because Claude generates code from high-level intent without a written contract. This skill forces a 10-minute thinking pass before any code generation. The PRD is the contract; the code must satisfy it; future-Abhillash can read the file three months from now and remember why.

The hard rule

No PRD, no code. When the trigger fires, refuse to generate code or vibe-code prompts until a PRD exists as a markdown file in the repo at /prds/YYYY-MM-DD-.md. This is non-negotiable except when the user explicitly overrides with "skip the PRD" — in which case flag the risk once, then proceed.

The 5-question protocol

Ask one question at a time. Wait for the answer. Do not batch. This matches the user's learning style (theory → quiz → build, one question at a time).

Each question has a quality bar. If the answer is vague, ask one follow-up. Then move on — don't gold-plate.

Question 1 — Problem:

What hurts today, and for whom?

Quality bar: a specific pain, not a feature wish. "I want a dashboard" is a feature; "I'm losing 30 minutes a day reconciling Stripe payouts against orders" is a problem. If they answer with a feature, ask: "What's the underlying pain that makes you want that?"

Question 2 — User:

Who specifically uses this, and what's their current alternative?

Quality bar: a real person (you, your team, a known segment) and a named alternative ("I do it in a spreadsheet now", "we use Notion but it doesn't sync"). If "everyone" — push back: "Pick the one user whose problem we're solving first."

Question 3 — Success:

One metric, one number, one timeframe — when do we know this worked?

Quality bar: measurable. "Faster reconciliation" fails. "Reconcile a day's payouts in under 3 minutes by end of week 2" passes. If they can't name a number, accept a binary: "Does the thing I described in Q1 still happen on Friday? Yes/No."

Read the full file on GitHub · 117 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. 11d ago First seen · 117 lines · 199 tokens per session scan A 7269381df03f

Subscribe to this mod's changes

prd-first is a skill published in the GitHub repository Abhillashjadhav/AI-PM-essential-skills (3 stars, last pushed 10d ago), licensed MIT. It adds 199 tokens to every session and 1,881 once invoked, about $0.0010 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.