product-sense

product-sense is a cursor rule for Cursor from ertra/pm-brain-for-cursor. It costs 386 tokens per session, scanned A, original, MIT.

A set of project rules that makes the agent ask product questions before writing a product brief or PRD, a document describing what to build and why.

In plain words
What is it for?
Use it when preparing product briefs, PRDs, one-page proposals, feature pitches, or similar documents in a repository.
Why use it?
It prevents rushed specifications based on an incomplete idea. It also makes the process clear when a brief already exists or when the user wants to skip the questions.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

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 rules/ertra/pm-brain-for-cursor/product-sense
Clone the repo
git clone --depth 1 https://github.com/ertra/pm-brain-for-cursor

Made for: Cursor.

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-sense

README.md
[![agentmods](https://agentmods.dev/badge/rules/ertra/pm-brain-for-cursor/product-sense.svg)](https://agentmods.dev/rules/ertra/pm-brain-for-cursor/product-sense)
Your own site
<a href="https://agentmods.dev/rules/ertra/pm-brain-for-cursor/product-sense"><img src="https://agentmods.dev/badge/rules/ertra/pm-brain-for-cursor/product-sense.svg" alt="Measured on agentmods" height="20"></a>
Per session 386 This file is loaded in full into every session.
When invoked 386 The same file — it is already loaded in full.
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 5.1 $0.00386 $0.00386
Opus 5 $0.00193 $0.00193
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00039 $0.00039

Measured 6d ago against content hash 2c9aa628c567, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

product-sense 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 6d 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.

.cursor/rules/product-sense.mdc · 21 lines

What it actually says

Product sense (coaching layer)

Before generating a product brief or PRD in this repo, follow PRODUCT-RULES.md.

  1. Read PRODUCT-RULES.md when the user asks for a brief, PRD, one-pager, feature pitch, or similar — including ad-hoc prompts (not only slash commands).
  2. Apply the "When the gate applies" table in that file:
    • Product brief → run the braindump gate (3–5 product-sense questions + sufficiency checklist) before opening templates or the create-product-brief skill's research step.
    • PRD → run the gate only if no brief exists (01-product-brief.md in the feature hub or an explicit brief path from the user). Otherwise proceed with the doc skill.
    • IFA, support article, competitive landscape, interview-frameworks → no braindump gate.
  3. Do not open 02-templates/ or write structured outlines until the sufficiency checklist passes or the user says "skip braindump" (log the override per PRODUCT-RULES.md).
  4. When a doc skill is invoked (create-product-brief, create-prd), follow that skill's Step 0.5 if present — it implements this gate in detail.

Doc pack workflow (order, feature hubs) remains in AGENTS.md and pm-brain-doc-workflow.mdc.

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. 6d ago First seen · 21 lines · 386 tokens per session scan A 2c9aa628c567

Subscribe to this mod's changes

product-sense is a cursor rule published in the GitHub repository ertra/pm-brain-for-cursor (22 stars, last pushed 3mo ago), licensed MIT. It adds 386 tokens to every session, about $0.0019 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.