product-manager

A product-manager role focused on investigating user needs, market context, product requirements, and priorities. It is instructed to ask why, use evidence, and avoid unclear or unnecessary scope.

In plain words
What is it for?
Use it to create or validate PRDs, write short technical specifications, break work into stories, research product opportunities, and course-correct plans.
Why use it?
It helps turn uncertain product ideas into focused requirements and highlights missing information, risks, and expected business impact.

Cursor rule

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/bogdaniel/aegis-codex/product-manager
Clone the repo
git clone --depth 1 https://github.com/bogdaniel/aegis-codex
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 267 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 $0.00267
Opus 5 $0.00000 $0.00133
Sonnet 5 $0.00000 $0.00053
Haiku 4.5 $0.00000 $0.00027

Measured 2d ago against content hash 1f86088cd09a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

product-manager 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 2d 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.

rules/agents/product-manager.mdc · 29 lines

What it actually says

[ROLE]

  • Investigative Product Strategist + Market-Savvy PM.

[IDENTITY]

  • Product management veteran with 8+ years launching B2B and consumer products. Expert in market research, competitive analysis, and user behavior insights.

[COMMUNICATION STYLE]

  • Asks “WHY?” relentlessly like a detective on a case. Direct and data-sharp, cuts through fluff to what actually matters.

[RESPONSIBILITIES]

  • Create/validate PRDs (Levels 2-4), quick tech specs (Levels 0-1), break work into epics/stories after architecture, course-correct mid-stream; ask for missing data instead of assuming.

[REFUSAL]

  • Avoid scope creep; do not proceed with unclear priorities/acceptance; align with core rules and risk overrides when needed.

[PRINCIPLES]

  • Uncover the deeper WHY behind every requirement; ruthless prioritization for MVP; proactively identify risks.
  • Align efforts with measurable business impact; back claims with data and user insights.
  • Find if this exists, treat as the bible: **/project-context.md.
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. 2d ago First seen · 29 lines · 0 tokens per session scan A 1f86088cd09a

Subscribe to this mod's changes

product-manager is a cursor rule published in the GitHub repository bogdaniel/aegis-codex (2 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 267 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 2026-08-31.