prp-prd

prp-prd is a command for coding agents from Fmarzochi/EGC. It costs 18 tokens per session (923 once invoked), scanned A, original, Apache-2.0.

An interactive tool for writing a Product Requirements Document, a plan that explains a product problem, its users, and the intended solution.

In plain words
What is it for?
Use it to define a product problem, test your assumptions, and produce a requirements document once the important questions are answered.
Why use it?
It turns an unclear idea into a documented plan by asking questions and separating known facts from assumptions and unanswered questions.

Command

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 commands/fmarzochi/egc/prp-prd
Clone the repo
git clone --depth 1 https://github.com/Fmarzochi/EGC

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 prp-prd

README.md
[![agentmods](https://agentmods.dev/badge/commands/fmarzochi/egc/prp-prd.svg)](https://agentmods.dev/commands/fmarzochi/egc/prp-prd)
Your own site
<a href="https://agentmods.dev/commands/fmarzochi/egc/prp-prd"><img src="https://agentmods.dev/badge/commands/fmarzochi/egc/prp-prd.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 923 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 $0.00018 $0.00923
Opus 5 $0.00009 $0.00462
Sonnet 5 $0.00004 $0.00185
Haiku 4.5 $0.00002 $0.00092

Measured yesterday against content hash 81c8416edec5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prp-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 yesterday.

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.

commands/prp-prd.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD Builder

Input: $ARGUMENTS

Build a Product Requirements Document by interviewing the user until the problem is understood, then writing the spec. The document is the output of the conversation, never a form filled in one shot.

Operating rule: the certainty board

Maintain a three-column board for the whole session:

Column Contents
Known Facts the user stated or evidence you gathered
Assumed Working hypotheses you adopted to move forward
Unknown Questions that still block a trustworthy spec

Every answer moves items between columns. You may only write the PRD when Unknown is empty or the user explicitly says "write it with what we have". Anything still in Assumed at writing time goes into the PRD's assumptions section, visible and testable.

Session flow

1. Seed

If $ARGUMENTS contains an idea, restate it in one sentence and place it in Assumed (it is a hypothesis, not a fact). If blank, open with exactly one question: "What problem keeps happening, and to whom?"

2. Question rounds

Ask in rounds of at most three questions. Never send a questionnaire. Pick the three questions that would eliminate the most Unknowns, favoring this order:

  1. Who has the problem and how do they cope today
  2. What evidence shows the problem is real (frequency, cost, complaints)
  3. What outcome would make the user say "solved"
  4. What must NOT change (constraints, integrations, budget)
  5. What happens if nothing is built

After each round, show the updated board in compact form so the user sees progress and can correct wrong Assumed entries.

3. Evidence pass

Before writing, verify what can be verified without the user:

  • Search the repo for related code, prior attempts, TODO markers
  • Check PRPs/prds/ for an earlier PRD on the same area
  • Note every verification in Known with its source

4. Write

Generate the document from the board. Kebab-case the title for the filename and save to:

PRPs/prds/{kebab-case-name}.prd.md

Read the full file on GitHub · 129 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. yesterday First seen · 129 lines · 18 tokens per session scan A 81c8416edec5

Subscribe to this mod's changes

prp-prd is a command published in the GitHub repository Fmarzochi/EGC (48 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 923 once invoked, about $0.0001 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 2026-09-03.