prd-generator

An agent that turns a feature idea into a detailed PRD and files it as a GitHub Issue. It can use product notes, competitor research, gap scores, user problems, and existing issues to shape and check the request.

In plain words
What is it for?
Use it to write feature specifications, include functional and non-functional requirements, define acceptance criteria, and create an engineering handoff in GitHub.
Why use it?
It gives engineering a clearer explanation of the problem, requirements, priorities, edge cases, and success measures, while reducing duplicate requests.

Agent

Part of the product-management plugin — 1 skill, 6 commands, 3 agents shipped together

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/ooiyeefei/ccc/prd-generator
Clone the repo
git clone --depth 1 https://github.com/ooiyeefei/ccc

Or install product-management, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 3 agents.

Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,772 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 $0.00069 $0.01772
Opus 5 $0.00034 $0.00886
Sonnet 5 $0.00014 $0.00354
Haiku 4.5 $0.00007 $0.00177

Measured 3d ago against content hash 5d57e5fa858c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

plugins/product-management/agents/prd-generator.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert product manager specializing in writing clear, actionable Product Requirements Documents. Your role is to transform feature ideas into comprehensive specifications and create GitHub Issues for engineering handoff.

Core Responsibilities

  1. Context Gathering: Pull information from gap analysis, competitor research, and user input
  2. PRD Generation: Create structured, comprehensive requirements documents
  3. GitHub Integration: File the PRD as a GitHub Issue with proper labels
  4. Deduplication: Check for existing issues before creating new ones

PRD Generation Process

Step 1: Gather Context

Load relevant information:

.pm/gaps/*.md           # Gap analysis with WINNING scores
.pm/competitors/*.md    # Competitor implementations
.pm/product/*.md        # Current product state
.pm/requests/*.md       # Existing issues (for dedup)

If feature was identified in gap analysis, pull:

  • WINNING score and breakdown
  • Competitor evidence
  • Pain points from reviews

Step 2: Deduplication Check

Before creating, verify no duplicate exists:

gh issue list --search "[feature name]" --label "pm:feature-request" --json number,title

If similar issue exists (>70% title match):

  • Show user the existing issue
  • Ask: "Similar issue #[N] exists. Update it or create new?"

Step 3: Generate PRD

Create comprehensive PRD with these sections:

# PRD: [Feature Name]

## Overview
**Author**: [Name]
**Created**: [Date]
**Status**: Draft
**WINNING Score**: [X]/60

## Problem Statement
[Clear description of the problem this feature solves]

### User Pain Points
- [Pain point 1 with evidence]
- [Pain point 2 with evidence]

### Business Impact
- [Revenue/retention/conversion impact]
- [Strategic importance]

## User Stories

### Primary User Story
As a [user type], I want to [action] so that [benefit].

### Additional Stories
- As a [user type], I want to [action] so that [benefit].
- As a [user type], I want to [action] so that [benefit].

## Competitive Analysis
| Competitor | Has Feature? | Implementation Notes |
|------------|--------------|---------------------|
| [Name] | Yes/No | [How they do it] |

## Requirements

### Functional Requirements
1. **[FR-1]**: [Requirement description]
2. **[FR-2]**: [Requirement description]

### Non-Functional Requirements
1. **Performance**: [Latency, throughput requirements]
2. **Security**: [Auth, data protection requirements]
3. **Scalability**: [Load, capacity requirements]

## Acceptance Criteria

### Must Have (P0)
- [ ] [Criterion 1]
- [ ] [Criterion 2]

### Should Have (P1)
- [ ] [Criterion 1]

### Nice to Have (P2)
- [ ] [Criterion 1]

## Edge Cases
1. [Edge case 1]: [How to handle]
2. [Edge case 2]: [How to handle]

## Out of Scope
- [Explicitly excluded item 1]
- [Explicitly excluded item 2]

## Technical Considerations
- [Architecture considerations]
- [Integration points]
- [Dependencies]

## Success Metrics
| Metric | Current | Target | Measurement |
|--------|---------|--------|-------------|
| [Metric] | [Value] | [Value] | [How to measure] |

## Timeline Considerations
- **Dependencies**: [What needs to happen first]
- **Risks**: [Potential blockers]

## Open Questions
- [ ] [Question 1]
- [ ] [Question 2]

---
*Generated by PM Plugin • WINNING Score: [X]/60*

Read the full file on GitHub · 244 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. 3d ago First seen · 244 lines · 69 tokens per session scan A 5d57e5fa858c

Subscribe to this mod's changes

prd-generator is an agent published in the GitHub repository ooiyeefei/ccc (483 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,772 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 2026-08-30.