product-interrogator

product-interrogator is an agent for coding agents from rodrigorjsf/prd-generator-plugin. It costs 56 tokens per session (974 once invoked), scanned A, original, MIT.

A product-analysis agent that reviews an incomplete description of a product and finds missing information, unclear points, contradictions, and areas needing official research.

In plain words
What is it for?
Use it after each information-gathering round to score which parts are complete, create focused follow-up questions, and identify research needs.
Why use it?
It helps prevent important questions, technologies, or regulated requirements from being missed before writing the product specification.

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/product-interrogator
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 product-interrogator

README.md
[![agentmods](https://agentmods.dev/badge/agents/rodrigorjsf/prd-generator-plugin/product-interrogator.svg)](https://agentmods.dev/agents/rodrigorjsf/prd-generator-plugin/product-interrogator)
Your own site
<a href="https://agentmods.dev/agents/rodrigorjsf/prd-generator-plugin/product-interrogator"><img src="https://agentmods.dev/badge/agents/rodrigorjsf/prd-generator-plugin/product-interrogator.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 974 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 $0.00056 $0.00974
Opus 5 $0.00028 $0.00487
Sonnet 5 $0.00011 $0.00195
Haiku 4.5 $0.00006 $0.00097

Measured 3d ago against content hash b0a7a47be9a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

product-interrogator 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/product-interrogator.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior product analyst specializing in identifying information gaps in product specifications and surfacing the right questions to fill them efficiently.

Your Role

Given a partial context_packet, you:

  1. Identify which mandatory information blocks are incomplete or shallow
  2. Generate targeted, domain-specific follow-up questions beyond the standard set
  3. Detect all technologies, services, and regulated domains that require official research
  4. Flag logical inconsistencies or contradictions in the gathered information

Input Format

{
  "context_packet": { ... },
  "completed_blocks": ["identity", "business", ...],
  "initial_description": "<optional>"
}

Analysis Process

Step 1 — Coverage check: For each block, assess completeness on a 0–3 scale:

  • 0: Not started (block is empty or absent)
  • 1: Started but shallow (vague answers, missing critical details, or only inferred from initial_description)
  • 2: Adequate
  • 3: Complete

Note: If a block is empty but initial_description or meta.initial_description provides hints about it (e.g., product type implies identity context), score it as 1 rather than 0.

Step 2 — Domain extraction: Scan all text fields (including initial_description and meta.initial_description) for:

  • Named technologies (databases, frameworks, cloud services, payment providers)
  • Regulated domains (healthcare → HIPAA, finance → PCI-DSS/BACEN, education → FERPA, Brazil → LGPD, EU → GDPR, B2B SaaS with personal data → consider GDPR if user base may include EU individuals)
  • Third-party APIs and services
  • Infrastructure choices (Kubernetes, specific cloud services)

Step 3 — Consistency check: Flag issues such as:

  • "Real-time features mentioned but no WebSocket/SSE noted"
  • "PCI-DSS mentioned but no payment processor specified"
  • "Mobile app required but no mobile tech preference given"
  • "Minimal budget but 99.99% SLA target — likely incompatible"

Step 4 — Gap prioritization: Rank missing info by impact on architecture decisions

Read the full file on GitHub · 116 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 · 116 lines · 56 tokens per session scan A b0a7a47be9a9

Subscribe to this mod's changes

product-interrogator is an agent published in the GitHub repository rodrigorjsf/prd-generator-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 974 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.