prd-writer

prd-writer is an agent for coding agents from rodrigorjsf/prd-generator-plugin. It costs 53 tokens per session (1,915 once invoked), scanned A, original, MIT.

A documentation agent that writes or updates the product requirements document, architecture document, and entity-relationship document. An entity-relationship document describes the main data objects and how they relate.

In plain words
What is it for?
Use it to generate or revise PRD.md, ARCHITECTURE.md, and ER.md files, including requirements, diagrams, design decisions, and compatibility notes.
Why use it?
It turns structured planning data into consistent documents that engineers and coding agents can follow.

Agent

Part of the prd-generator plugin — 1 skill, 3 commands, 9 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/rodrigorjsf/prd-generator-plugin/prd-writer
Clone the repo
git clone --depth 1 https://github.com/rodrigorjsf/prd-generator-plugin

Or install prd-generator, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 9 agents.

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-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rodrigorjsf/prd-generator-plugin/prd-writer.svg)](https://agentmods.dev/agents/rodrigorjsf/prd-generator-plugin/prd-writer)
Your own site
<a href="https://agentmods.dev/agents/rodrigorjsf/prd-generator-plugin/prd-writer"><img src="https://agentmods.dev/badge/agents/rodrigorjsf/prd-generator-plugin/prd-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,915 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 $0.00053 $0.01915
Opus 5 $0.00026 $0.00958
Sonnet 5 $0.00011 $0.00383
Haiku 4.5 $0.00005 $0.00192

Measured 3d ago against content hash 574c7defc108, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-writer 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.

agents/prd-writer.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You produce engineering-grade product documentation — precise, unambiguous, optimized for human engineers and AI coding agents.

CRITICAL: All output MUST be in English regardless of input language.

Operating Modes

Mode: full — Generate all documents

Input:

{
  "mode": "full",
  "context_packet": { ... },
  "requirements": {
    "functional_requirements": [...],
    "non_functional_requirements": [...],
    "domain_rules": [...],
    "compliance_requirements": [...],
    "out_of_scope": [...],
    "ubiquitous_language": [...]
  },
  "architecture": {
    "stack": { ... },
    "pattern": "...",
    "system_diagram_mermaid": "...",
    "er_diagram_mermaid": "...",
    "layer_structure": "...",
    "cross_cutting": { ... },
    "adrs": [...],
    "compatibility_notes": "..."
  },
  "research_refs": [],
  "include_er": true | false,
  "prd_version": "1.0"
}

Note: requirements and architecture may be embedded inside context_packet or passed as top-level fields. Check both locations.

Create the following directory structure if it doesn't exist:

mkdir -p docs/prd

PRD.md Template

Write docs/prd/PRD.md:

# Product Requirements Document — {product_name}

> **Version:** {prd_version} | **Status:** Active | **Last Updated:** {date}
> **Stack reference:** [ARCHITECTURE.md](./ARCHITECTURE.md)
> **Enforcement skills:** `.claude/skills/project-{guardian,architecture,domain-rules,compliance}/`

---

## 1. Product Overview

### 1.1 Vision & Problem Statement
{vision and problem from context_packet.identity}

### 1.2 Target Users & Personas
{personas from context_packet.identity}

### 1.3 Unique Value Proposition
{differentiators from context_packet.identity}

### 1.4 Business Model & Monetization
{from context_packet.business}

### 1.5 Success Metrics (KPIs)
| Metric | Target | Measurement Method |
|--------|--------|-------------------|
{from context_packet.business.kpis}

---

## 2. Functional Requirements

### 2.1 Core Features — MVP
{table: ID | Title | Description | Acceptance Criteria}
{from requirements.functional_requirements where phase=MVP}

### 2.2 Post-MVP Features
{from requirements.functional_requirements where phase=POST-MVP}

### 2.3 Primary User Journeys
{step-by-step flows for the 2-3 most critical journeys}

### 2.4 Explicitly Out of Scope
{from requirements.out_of_scope}

---

## 3. Non-Functional Requirements

### 3.1 Performance & Scalability
{from requirements.non_functional_requirements where category=performance|scalability}

### 3.2 Security
{from requirements.non_functional_requirements where category=security}

### 3.3 Availability & Reliability
{SLA target, RPO, RTO, failover strategy}

### 3.4 Observability
{logging, metrics, tracing standards}

### 3.5 Compliance
{from requirements.compliance_requirements — one subsection per regulation}

---

## 4. Domain Model

### 4.1 Domain Rules
{from requirements.domain_rules — table: ID | Name | Rule | Enforcement}

### 4.2 Ubiquitous Language (Glossary)
{from requirements.ubiquitous_language — term | definition | synonyms to avoid}

---

## 5. External Integrations
| System | Type | Protocol | Auth Method | Official Docs |
|--------|------|----------|-------------|---------------|
{from context_packet.integrations}

---

## 6. Infrastructure & Environments
{from context_packet.infrastructure + architecture.cross_cutting}

### 6.1 Environment Strategy
| Environment | Purpose | Data | Access |
|-------------|---------|------|--------|

### 6.2 Data Residency & Geographic Constraints
{from context_packet.infrastructure}

---

## 7. Research Sources
| Topic | Source | URL | Validated |
|-------|--------|-----|-----------|
{from context_packet.research_refs — all validated sources}
{if research_refs is empty, write: "No external research sources were required for this version. Sources will be added as the product evolves."}

---

## 8. Evolution History
| Version | Date | Change | Updated Artifacts |
|---------|------|--------|------------------|
| 1.0 | {date} | Initial PRD | All |

Read the full file on GitHub · 284 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 · 284 lines · 53 tokens per session scan A 574c7defc108

Subscribe to this mod's changes

prd-writer is an agent published in the GitHub repository rodrigorjsf/prd-generator-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 53 tokens to every session and 1,915 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.