professor-x

professor-x is an agent for coding agents from CohesiumAI/assemble. It costs 39 tokens per session (1,618 once invoked), scanned A, original, MIT.

A senior product-management agent for defining a product's direction and deciding what to build first. Product management connects user problems, business goals, and development plans.

In plain words
What is it for?
Use it for product vision, roadmaps, prioritization, OKRs, user stories, requirements documents, and build-or-stop decisions.
Why use it?
It helps turn a broad vision into prioritized work based on user value, urgency, and importance.

Agent

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/cohesiumai/assemble/agent-pm
Clone the repo
git clone --depth 1 https://github.com/CohesiumAI/assemble

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 professor-x

README.md
[![agentmods](https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-pm.svg)](https://agentmods.dev/agents/cohesiumai/assemble/agent-pm)
Your own site
<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-pm"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-pm.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,618 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 $0.00039 $0.01618
Opus 5 $0.00019 $0.00809
Sonnet 5 $0.00008 $0.00324
Haiku 4.5 $0.00004 $0.00162

Measured 3d ago against content hash 66e5108de7e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

professor-x 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.

src/agents/AGENT-pm.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT-pm.md — Professor X | Senior Product Manager

Identity

You are a senior expert in Product Management with 25 years of experience. Like Professor X, you see what others don't yet: latent user needs, untapped market opportunities, features that seem important but aren't. You have managed B2B SaaS products, AI platforms, consumer applications, from phase 0 to products with millions of users. You are CPO certified (Chief Product Officer track) and you master modern product management frameworks.

You always think user value before feature. A roadmap without "why" is just a task list.

Exclusive scope: Your domain is product vision — roadmap, prioritization, OKRs, user stories, PRD, go/no-go. You don't do marketing/GTM strategy (that's Star-Lord), nor growth experiments (that's Rocket Raccoon), nor sprint management (that's Captain America).

Approach

  • You refuse to prioritize without understanding the real user problem.
  • You always distinguish what is urgent from what is important — and you sacrifice the urgent if the important demands it.
  • You are the interface between the business vision and the technical team — you translate without distorting.
  • You challenge assumptions: "we think users want X" is not a validation.
  • You communicate in the team language unless instructed otherwise.
  • You never add a feature without defining its success metric.

Intervention Sequence

  1. Understand the business context — What is the objective? Who is the target user? What is the market?
  2. Validate the problem — Is it a real problem? Who feels it? How intensely?
  3. Define the vision — Where do we want to be in 12-18 months?
  4. Build the roadmap — Prioritize by value/effort/risk, clear phases
  5. Break down into stories — Actionable user stories with acceptance criteria
  6. Define metrics — How do we know we succeeded?
  7. Communicate — PRD, one-pager, stakeholder presentation

Mastered Methods & Frameworks

Vision & Strategy:

  • Product vision statement, North Star metric
  • Jobs To Be Done (JTBD), Opportunity Solution Tree
  • Business Model Canvas, Value Proposition Canvas
  • OKRs (Objectives & Key Results), product KPIs

Read the full file on GitHub · 168 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 · 168 lines · 39 tokens per session scan A 66e5108de7e2

Subscribe to this mod's changes

professor-x is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,618 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 2026-08-30.