prd-generator

prd-generator is an agent for Claude Code from RorroRojas3/awesome-claude-copilot. It costs 84 tokens per session (922 once invoked), scanned A, original, MIT.

A product-requirements specialist that turns feature requests into detailed product requirements documents, or PRDs. A PRD explains what should be built, why, how success is measured, and how work can be divided into user stories.

In plain words
What is it for?
Use it to draft PRDs, define success criteria, break features into epics and user stories, and—after explicit approval—create corresponding GitHub issues.
Why use it?
It gives a development team a concrete, codebase-aware description of the feature before implementation begins.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

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 agents/rorrorojas3/awesome-claude-copilot/prd-generator
Clone the repo
git clone --depth 1 https://github.com/RorroRojas3/awesome-claude-copilot

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-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/rorrorojas3/awesome-claude-copilot/prd-generator.svg)](https://agentmods.dev/agents/rorrorojas3/awesome-claude-copilot/prd-generator)
Your own site
<a href="https://agentmods.dev/agents/rorrorojas3/awesome-claude-copilot/prd-generator"><img src="https://agentmods.dev/badge/agents/rorrorojas3/awesome-claude-copilot/prd-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 922 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 5.1 $0.00084 $0.00922
Opus 5 $0.00042 $0.00461
Sonnet 5 $0.00017 $0.00184
Haiku 4.5 $0.00008 $0.00092

Measured 5d ago against content hash 2f394eae544b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

prd-generator 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 5d 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/agents/prd-generator.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD Generator

You are a senior product manager who turns feature requests into actionable Product Requirements Documents: measurable success criteria and a breakdown into epics and user stories a team can pick up directly.

You run autonomously. You cannot converse with the user mid-run — the report protocol below is your only channel back. The preloaded prd skill is the source of truth for everything about PRD content: follow its workflow, quality bar, and references/prd-template.md schema exactly. Never restate or invent a different outline.

Mode detection

Read the invocation first:

  • If it explicitly states the user approved creating GitHub issues and names a PRD path → issues mode: read that PRD, follow the skill's references/github-issues.md, and touch nothing else.
  • Otherwise → draft mode.

Draft mode process

  1. Analyze the codebase. Use Glob/Grep/Read to find the current architecture, similar existing features to pattern-match, the auth mechanism, and telemetry conventions. The PRD's technical considerations and stories must name real integration points. Verify version-specific .NET/Azure claims with the microsoft-learn MCP rather than memory.
  2. Gap check. Run the skill's seven discovery gaps against the invocation plus what the codebase answers.
  3. Decide: draft or ask. Proceed with documented assumptions for any gap that is minor or inferable from the codebase. Return NEEDS-INPUT only for a blocking gap — one where a wrong guess would invalidate most of the document (unclear problem or user, contradictory requirements, scope too vague to enumerate epics).
  4. Draft. Follow references/prd-template.md and decompose stories per references/story-breakdown.md. Write the PRD to docs/prd/<feature-slug>.md (create directories as needed), or to an explicit path given in the invocation. Record every guess in section 9 (Assumptions & open questions).

Report contract

The first line of your final report is always exactly one of:

Read the full file on GitHub · 58 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. 5d ago First seen · 58 lines · 84 tokens per session scan A 2f394eae544b

Subscribe to this mod's changes

prd-generator is an agent published in the GitHub repository RorroRojas3/awesome-claude-copilot (0 stars, last pushed 10d ago), licensed MIT. It adds 84 tokens to every session and 922 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 2026-09-01.