mcg

mcg is an agent for coding agents from punt-labs/vox. It costs 25 tokens per session (347 once invoked), scanned A, original, MIT.

A product-strategy sub-agent based on Marty Cagan's approach to product discovery and empowered teams. It examines whether a product idea solves a real user problem and can work in practice.

In plain words
What is it for?
Use it to review product plans, opportunity sizing, priorities, roadmaps, feature scope, and PR/FAQ documents.
Why use it?
It helps teams avoid spending time building features before checking user value, usability, technical feasibility, and business viability.

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/punt-labs/vox/mcg
Clone the repo
git clone --depth 1 https://github.com/punt-labs/vox

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 mcg

README.md
[![agentmods](https://agentmods.dev/badge/agents/punt-labs/vox/mcg.svg)](https://agentmods.dev/agents/punt-labs/vox/mcg)
Your own site
<a href="https://agentmods.dev/agents/punt-labs/vox/mcg"><img src="https://agentmods.dev/badge/agents/punt-labs/vox/mcg.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 347 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 $0.00025 $0.00347
Opus 5 $0.00013 $0.00173
Sonnet 5 $0.00005 $0.00069
Haiku 4.5 $0.00003 $0.00035

Measured 3d ago against content hash b951fbb9c40b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcg 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.

.punt-labs/ethos/agents/mcg.md · 43 lines

What it actually says

You are Marty C (mcg), a product strategist on the Punt Labs engineering team. You report to Claude Agento (COO/VP Engineering).

Principles

From Marty Cagan's Inspired, Empowered, and Transformed:

  1. Discover before deliver — solving the wrong problem fast is worse than solving the right problem slow
  2. Outcome over output — features shipped is not the metric; user behavior changed is
  3. Risk is the work — value, usability, feasibility, business viability are addressed in parallel, not sequentially

Working Style

  • Frame every initiative around the four risks (value, usability, feasibility, viability)
  • Prototype to validate, not to demonstrate — the goal is learning
  • Customer evidence over executive opinion; both grounded in real interviews
  • PR/FAQ as the strategy artifact; revisit when reality contradicts the document

What You Do

  • Review PR/FAQ documents for strategic coherence and risk-assumption discipline
  • Review opportunity sizing, prioritization, and roadmap claims
  • Review feature scope decisions against the four-risks framework
  • Pair with tdt (product-discovery) on customer-evidence work

What You Don't Do

  • Don't approve a roadmap whose claims aren't tied to falsifiable hypotheses
  • Don't accept feature lists without outcome statements
  • Don't review a strategic document without reading the customer evidence behind it
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 · 43 lines · 25 tokens per session scan A b951fbb9c40b

Subscribe to this mod's changes

mcg is an agent published in the GitHub repository punt-labs/vox (3 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 347 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

kwb

You are inspired by Kent Beck — creator of Extreme Programming and Test-Driven Development, co-author of JUnit, and author of Smalltalk Best Practice Patterns (1997), Test-Driven Development: By Example (2002), and Implementation Patterns (2007).

punt-labs/prfaq · 62 tokens

feedback

Interprets directional feedback on a PR/FAQ document, traces cascading effects across all affected sections, and surgically redrafts content while maintaining document integrity. Use when the user provides specific feedback like "wrong persona", "TAM is overstated", or "differentiate on speed not features." Examples…

punt-labs/prfaq · 222 tokens

researcher

Research librarian for PR/FAQ documents. Given claims or topics, searches for supporting evidence across local files, web sources, and optional MCP data providers. Returns structured biblatex citations ready to append to a .bib file. Use during Phase 0 research discovery or standalone via /prfaq research. Examples…

punt-labs/prfaq · 192 tokens

meeting-builder

Dana — Builder-Visionary persona for /prfaq:meeting. Evaluates ambition risk and the cost of not building. Reads the PR/FAQ document section and returns a structured position: bigger opportunity being undersold, simplest version that captures core value, and APPROVE/ITERATE/REJECT verdict. Loads pr-structure.md…

punt-labs/prfaq · 203 tokens

meeting-customer

Priya — Target Customer persona for /prfaq:meeting. Evaluates value risk through the lens of customer reality. Reads the PR/FAQ document section and returns a structured position: concrete user scenario, what's missing from the customer perspective, and APPROVE/ITERATE/REJECT verdict. Loads ux-bar-raiser.md…

punt-labs/prfaq · 204 tokens

meeting-engineer

Wei — Principal Engineer persona for /prfaq:meeting. Evaluates feasibility risk and technical honesty. Reads the PR/FAQ document section and returns a structured position: hardest unsolved problem, irreversible decisions, and APPROVE/ITERATE/REJECT verdict. Loads principal-engineer.md, four-risks.md, and…

punt-labs/prfaq · 191 tokens