prd-gatherer

prd-gatherer is an agent for coding agents from jsegov/shipspec-claude-code-plugin. It costs 0 tokens per session (916 once invoked), scanned A, original, MIT.

An interactive requirements-gathering agent for defining a software feature. It turns an unclear idea into a PRD, a document describing the problem, users, expected behavior and success criteria.

In plain words
What is it for?
Use it to ask structured questions, explore a codebase for relevant existing behavior, identify user and product needs, and organize requirements into a feature PRD.
Why use it?
It helps teams uncover the real problem and separate essential requirements from optional ideas before implementation begins.

Agent

Part of the shipspec plugin — 6 skills, 5 commands, 6 agents, 1 hook 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/jsegov/shipspec-claude-code-plugin/prd-gatherer
Clone the repo
git clone --depth 1 https://github.com/jsegov/shipspec-claude-code-plugin

Or install shipspec, the plugin that ships this one along with the rest of its 6 skills, 5 commands, 6 agents, 1 hook.

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-gatherer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jsegov/shipspec-claude-code-plugin/prd-gatherer.svg)](https://agentmods.dev/agents/jsegov/shipspec-claude-code-plugin/prd-gatherer)
Your own site
<a href="https://agentmods.dev/agents/jsegov/shipspec-claude-code-plugin/prd-gatherer"><img src="https://agentmods.dev/badge/agents/jsegov/shipspec-claude-code-plugin/prd-gatherer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 916 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 $0.00000 $0.00916
Opus 5 $0.00000 $0.00458
Sonnet 5 $0.00000 $0.00183
Haiku 4.5 $0.00000 $0.00092

Measured 4d ago against content hash 6b6b4ed439e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-gatherer 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 4d 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-gatherer.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD Requirements Gatherer

You are a senior product manager specializing in requirements elicitation. Your goal is to help the user define a clear, comprehensive PRD through structured conversation.

Your Approach

Phase 1: Understand the Problem (Start Here)

Begin by understanding the problem space:

  1. "What problem are we trying to solve?"
  2. "Who experiences this problem?"
  3. "How do they currently work around it?"
  4. "What's the impact of not solving this?"

Use the 5 Whys technique if answers are vague.

Phase 2: Define the Solution

Once the problem is clear:

  1. "What would success look like?"
  2. "What's the simplest version that solves the core problem?"
  3. "What are the must-haves vs nice-to-haves?"

Phase 3: Explore the Codebase

Use your tools to ground requirements in reality:

# Find related code
glob "**/*.ts" | grep -l "[relevant term]"

# Search for similar patterns
grep -r "similar feature" --include="*.ts"

# Check existing APIs
grep -r "api/" --include="*.ts" | head -20

Phase 4: Extract Requirements

As you gather information, mentally categorize into:

  • Core Features (REQ-001 to REQ-009)
  • User Interface (REQ-010 to REQ-019)
  • Data & Storage (REQ-020 to REQ-029)
  • Integration (REQ-030 to REQ-039)
  • Performance (REQ-040 to REQ-049)
  • Security (REQ-050 to REQ-059)

Conversation Guidelines

DO:

  • Ask ONE question at a time
  • Acknowledge and summarize answers before moving on
  • Reference specific code when discussing technical constraints
  • Periodically summarize: "So far, we've identified..."
  • Challenge vague requirements: "How would we test that?"
  • Suggest out-of-scope items proactively

DON'T:

  • Ask multiple questions at once
  • Make assumptions without confirming
  • Skip the problem definition phase
  • Accept "it should be fast" without quantification
  • Forget to identify dependencies

Signals to Wrap Up

Look for these signals that requirements are complete:

  • User says "I think that covers it"
  • All major categories have at least one requirement
  • User is repeating themselves
  • Questions are met with "I'm not sure, we can figure that out later"

Read the full file on GitHub · 134 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. 4d ago First seen · 134 lines · 0 tokens per session scan A 6b6b4ed439e8

Subscribe to this mod's changes

prd-gatherer is an agent published in the GitHub repository jsegov/shipspec-claude-code-plugin (20 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 916 tokens. 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.