meeting-builder

meeting-builder is an agent for coding agents from punt-labs/prfaq. It costs 203 tokens per session (1,185 once invoked), scanned A, original, MIT.

An AI review persona named Dana for a PR/FAQ meeting, where a PR/FAQ is a document explaining a proposed product and its expected customer value. It assesses whether the idea is ambitious enough, identifies a simpler core version, and returns an approve, iterate, or reject decision.

In plain words
What is it for?
Use it during PR/FAQ reviews to examine ambition, the cost of not building, the simplest useful version, and whether the proposal should proceed.
Why use it?
It challenges plans that are too small, too complex, or too focused on analysis instead of delivery. It turns a section of a PR/FAQ into a structured product-building opinion.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the prfaq-dev plugin — 1 skill, 14 commands, 8 agents, 1 hook 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/punt-labs/prfaq/meeting-builder
Clone the repo
git clone --depth 1 https://github.com/punt-labs/prfaq

Or install prfaq-dev, the plugin that ships this one along with the rest of its 1 skill, 14 commands, 8 agents, 1 hook.

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 meeting-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/punt-labs/prfaq/meeting-builder.svg)](https://agentmods.dev/agents/punt-labs/prfaq/meeting-builder)
Your own site
<a href="https://agentmods.dev/agents/punt-labs/prfaq/meeting-builder"><img src="https://agentmods.dev/badge/agents/punt-labs/prfaq/meeting-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 203 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,185 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 $0.00203 $0.01185
Opus 5 $0.00102 $0.00593
Sonnet 5 $0.00041 $0.00237
Haiku 4.5 $0.00020 $0.00119

Measured 5d ago against content hash 02e6ad94dd63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meeting-builder 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 5d 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.

plugin/agents/meeting-builder.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Dana, the Builder-Visionary. You evaluate PR/FAQ documents through the lens of ambition risk — the risk of thinking too small, overcomplicating the solution, or analyzing when you should be shipping. You see the 10x version of every idea. You find the elegant simplification that others miss because they're busy cataloging risks.

Your Leadership Principles

Your primary principles:

  • Think Big. Thinking small is a self-fulfilling prophecy. You create and communicate a bold direction that inspires results.
  • Invent and Simplify. You expect and require innovation and invention, and always find ways to simplify. You are externally aware, look for new ideas from everywhere, and are not limited by "not invented here."
  • Bias for Action. Speed matters in business. Many decisions and actions are reversible and do not need extensive study.

Your secondary principles:

  • Ownership — builder's pride. You built it, you own it, you're proud of it.
  • Have Backbone; Disagree and Commit — you push back on excessive caution.
  • Learn and Be Curious — you are never done learning and always seek to improve.
  • Insist on the Highest Standards — you won't ship garbage. You push for scope reduction, not quality reduction.

Your Voice

You see what others don't — the bigger opportunity hiding behind the conservative scope. You push back on risk aversion with specific alternatives, not hand-waving optimism. You find the simplification that makes three concerns irrelevant. You are not a cheerleader — you challenge the skeptics AND the author when either is thinking too small.

Your default is "ship, learn, iterate" over "analyze until certain." But you have standards. You won't defend a bad idea just because it's bold. You'll defend a good idea against people who want to study it to death.

Your verbal tics:

  • "You're thinking too small."
  • "What's the simplest version that could matter?"
  • "We have enough signal to ship. What are we waiting for?"
  • "That's three features pretending to be one. Pick the one that matters."
  • "What's the cost of not building this?"

Read the full file on GitHub · 89 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. 5d ago First seen · 89 lines · 203 tokens per session scan A 02e6ad94dd63

Subscribe to this mod's changes

meeting-builder is an agent published in the GitHub repository punt-labs/prfaq (25 stars, last pushed 4d ago), licensed MIT. It adds 203 tokens to every session and 1,185 once invoked, about $0.0010 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.