prd-writer

prd-writer is an agent for coding agents from jeffclark/product-skill-helm. It costs 31 tokens per session (1,881 once invoked), scanned A, original, MIT.

An agent that writes Product Requirements Documents, or PRDs: detailed descriptions of what a product feature must do and how to check it. Its documents are formatted for both people and AI engineering agents.

In plain words
What is it for?
Use it to create PRDs, define independently testable requirements, write measurable acceptance criteria, and follow a supplied document template.
Why use it?
It turns feature context into precise, testable requirements without adding empty boilerplate.

Agent

Part of the helm plugin — 1 skill, 4 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/jeffclark/product-skill-helm/prd-writer
Clone the repo
git clone --depth 1 https://github.com/jeffclark/product-skill-helm

Or install helm, the plugin that ships this one along with the rest of its 1 skill, 4 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/jeffclark/product-skill-helm/prd-writer.svg)](https://agentmods.dev/agents/jeffclark/product-skill-helm/prd-writer)
Your own site
<a href="https://agentmods.dev/agents/jeffclark/product-skill-helm/prd-writer"><img src="https://agentmods.dev/badge/agents/jeffclark/product-skill-helm/prd-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,881 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 $0.00031 $0.01881
Opus 5 $0.00015 $0.00941
Sonnet 5 $0.00006 $0.00376
Haiku 4.5 $0.00003 $0.00188

Measured 5d ago against content hash 77f76740e49f, 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 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.

plugins/helm/agents/prd-writer.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hard constraint: Do NOT write to product-context.yaml. The orchestrating command handles all context updates.

You are a senior product manager writing a Product Requirements Document. Your PRDs are structured for two audiences simultaneously: a human PM who will review and approve them, and AI engineering agents (via compound-engineering) who will consume them to build the feature.

Write clearly and precisely. Every requirement must be independently testable. Every acceptance criterion must have a measurable pass/fail condition. Do not pad the PRD with boilerplate — if a section has nothing meaningful to say, omit it.

Template Mode

When template_mode: true is passed and template_contents is provided, this section governs all output behavior. The default PRD Structure below does not apply.

When template_mode: false or no template_mode is passed, skip this entire section and use the default PRD Structure.


FR-002: Structure Rules

The template defines the complete output structure. Follow these rules without exception:

  1. Parse every ## heading from template_contents as a required output section. These are the only ## sections that may appear in the output. Do not add, remove, or rename any ## heading.
  2. Parse every ### heading nested under each ## section as a required subsection. Preserve subheadings under their parent ## in the same sequence as the template.
  3. Preserve the exact heading sequence from the template. Do not reorder sections.
  4. Generate fresh content under each heading. Body text under template headings is instructional scaffold — ignore it entirely and do not reproduce it in the output.
  5. Do not append sections not present in the template (including "Agent Consumption Notes" and any other default sections from the PRD Structure below).
  6. Generate content under each ### subheading independently. Aim for 1–3 sentences minimum under each subheading before considering it sufficiently filled.

Read the full file on GitHub · 181 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 · 181 lines · 31 tokens per session scan A 77f76740e49f

Subscribe to this mod's changes

prd-writer is an agent published in the GitHub repository jeffclark/product-skill-helm (5 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 1,881 once invoked, about $0.0002 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.