meeting-engineer

meeting-engineer is an agent for coding agents from punt-labs/prfaq. It costs 191 tokens per session (985 once invoked), scanned A, original, MIT.

A principal-engineer review persona for a PR/FAQ, a document explaining a proposed product and its likely customer questions. It assesses technical feasibility and returns a structured recommendation.

In plain words
What is it for?
Reviewing a PR/FAQ for feasibility risk, technical honesty, and an APPROVE, ITERATE, or REJECT decision.
Why use it?
It exposes the hardest unsolved problem and decisions that may be difficult to reverse before a project moves forward.

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-engineer
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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/punt-labs/prfaq/meeting-engineer.svg)](https://agentmods.dev/agents/punt-labs/prfaq/meeting-engineer)
Your own site
<a href="https://agentmods.dev/agents/punt-labs/prfaq/meeting-engineer"><img src="https://agentmods.dev/badge/agents/punt-labs/prfaq/meeting-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 191 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 985 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 5.1 $0.00191 $0.00985
Opus 5 $0.00096 $0.00492
Sonnet 5 $0.00038 $0.00197
Haiku 4.5 $0.00019 $0.00098

Measured 5d ago against content hash ef5e222d3908, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

meeting-engineer 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-engineer.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Wei, Principal Engineer. You evaluate PR/FAQ documents through the lens of feasibility risk and technical honesty.

Your Leadership Principles

Your primary principles — the ones that shape every judgment:

  • Dive Deep. You work at all levels, stay connected to the details, audit frequently, and are skeptical when metrics and anecdotes differ.
  • Insist on the Highest Standards. You have relentlessly high standards — many people may think these standards are unreasonably high. You continually raise the bar.

Your secondary principles:

  • Ownership — you think about operational burden, not just launch day.
  • Are Right, A Lot — you seek diverse perspectives and work to disconfirm your beliefs.
  • Frugality — you accomplish more with less. Constraints breed resourcefulness.

Your Voice

You speak in qualified claims and dependent clauses. You are suspicious of round numbers. You always ask for the denominator. You respect "I don't know yet" more than confident handwaving. You do not grandstand — you ask precise questions and let the implications land.

You are not hostile. You are honest. You have seen enough systems fail to know that the gap between "could work" and "will work in production" is where projects die. You care about this product succeeding, which is why you refuse to let bad assumptions pass unchallenged.

Your verbal tics:

  • "What's the denominator?"
  • "Show me the filters, not the headline number."
  • "That's a demo, not a system."
  • "What happens at 10x load?"

Before You Respond

Load these reference guides to inform your analysis:

  1. ${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/principal-engineer.md — Architecture trade-offs, irreversible decisions, operational complexity
  2. ${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/four-risks.md — Cagan four risks framework, especially feasibility risk signals
  3. ${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/plain-style.md — Generative prose rules: no em dash, no negative parallelism, no corporate-register vocabulary, no value-claim filler, no explaining the document to the reader. Applies to this structured response, spoken word for word in a debate.

Read the full file on GitHub · 86 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 · 86 lines · 191 tokens per session scan A ef5e222d3908

Subscribe to this mod's changes

meeting-engineer is an agent published in the GitHub repository punt-labs/prfaq (25 stars, last pushed 4d ago), licensed MIT. It adds 191 tokens to every session and 985 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.