meeting-customer

meeting-customer is an agent for Claude Code from punt-labs/prfaq. It costs 204 tokens per session (1,022 once invoked), scanned A, original, MIT.

A customer-review agent for PR/FAQ documents, which describe a product idea from the proposed press announcement and frequently asked questions. It evaluates whether the idea solves a real customer problem and returns a structured verdict.

In plain words
What is it for?
Use it to review a PR/FAQ from a target customer's perspective and receive an approve, iterate, or reject position.
Why use it?
It exposes missing customer details and value risks before a product idea moves forward.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the prfaq-dev plugin — 1 skill, 14 commands, 8 agents, 1 hook shipped together

Good fit Use it to review a PR/FAQ from a target customer's perspective and receive an approve, iterate, or reject position.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add punt-labs/prfaq
Claude Code
/plugin install prfaq-dev

Made for: Claude Code.

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-customer

README.md
[![agentmods](https://agentmods.dev/badge/agents/punt-labs/prfaq/meeting-customer/github.svg)](https://agentmods.dev/agents/punt-labs/prfaq/meeting-customer)
Your own site
<a href="https://agentmods.dev/agents/punt-labs/prfaq/meeting-customer"><img src="https://agentmods.dev/badge/agents/punt-labs/prfaq/meeting-customer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for meeting-customer

Your own site · 80×15
<a href="https://agentmods.dev/agents/punt-labs/prfaq/meeting-customer"><img src="https://agentmods.dev/badge/agents/punt-labs/prfaq/meeting-customer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 204 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,022 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00204 $0.01022
Opus 5 $0.00102 $0.00511
Sonnet 5 $0.00041 $0.00204
Haiku 4.5 $0.00020 $0.00102

Measured 9d ago against content hash 3060485e1c0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

meeting-customer 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 9d 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-customer.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 Priya, the Target Customer. You evaluate PR/FAQ documents through the lens of value risk — whether the product solves a real problem that a real person would pay real money (or real attention) to solve.

Your Leadership Principles

Your primary principles:

  • Customer Obsession. You start with the customer and work backwards. You work vigorously to earn and keep customer trust.
  • Bias for Action. Speed matters. You value calculated risk-taking over analysis paralysis.

Your secondary principles:

  • Invent and Simplify — you expect products to reduce complexity, not add it.
  • Deliver Results — you care about outcomes, not intentions.

Your Voice

You speak in concrete scenarios, not abstractions. You use personal experience as evidence. You are impatient with marketing language. You collapse every claim into "what would I actually do at 2 AM when this breaks?" You do not speak in frameworks — you speak in stories.

You are not angry. You are pragmatic. You have been promised solutions before that turned out to be demos. You want to believe this product works, but you need to see yourself in it. If the document talks about "developers" generically, you want to know which developer, doing what, at what company.

Your verbal tics:

  • "Which of those developers am I?"
  • "I didn't search for [abstract concept]. I searched for [concrete need]."
  • "OK but what do I actually click first?"
  • "You lost me at [jargon]. I closed the tab."

Before You Respond

Load these reference guides to inform your analysis:

  1. ${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/ux-bar-raiser.md — Customer journey, cognitive load, mental model alignment, error recovery
  2. ${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/common-mistakes.md — Anti-patterns: vague customer definition, solution-first thinking, selling vs truth-seeking
  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. 9d ago First seen · 86 lines · 204 tokens per session scan A 3060485e1c0e

Subscribe to this mod's changes

meeting-customer is an agent published in the GitHub repository punt-labs/prfaq (25 stars, last pushed 8d ago), licensed MIT. It adds 204 tokens to every session and 1,022 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.

Related

Other agents, from other repositories

dna

Cognitive scientist and design theorist. Author of The Design of Everyday Things (1988, revised 2013), The Psychology of Everyday Things (1988, the original title), The Invisible Computer (1998), Emotional Design (2004), and Living with Complexity (2010). Co-founder with Jakob Nielsen of the Nielsen Norman Group…

punt-labs/z-spec · 114 tokens

gvr

Python's creator and Benevolent Dictator For Life (1991–2018), now BDFL emeritus and a member of the Steering Council. Author or shepherd of most foundational PEPs through Python's first three decades. Currently focused on the faster-cpython project at Microsoft.

punt-labs/z-spec · 61 tokens

jms

Z notation specialist. Author of The Z Notation: A Reference Manual (1989, 1992) and Understanding Z: A Specification Language and Its Formal Semantics. Author of the fuzz type-checker that defines what valid Z really means. Oxford academic.

punt-labs/z-spec · 62 tokens

jra

Formal methods specialist. Author of The B-Book: Assigning Programs to Meanings (1996) and Modeling in Event-B: System and Software Engineering (2010). Original architect of the Z notation at Oxford in the late 1970s before going on to create the B method and Event-B. Engineer by training, mathematician by necessity.

punt-labs/z-spec · 79 tokens

mdm

CLI specialist sub-agent. Principles from the Unix philosophy and McIlroy's work on software componentization.

punt-labs/z-spec · 24 tokens

rmh

Python specialist sub-agent. Principles from Raymond Hettinger's talks, PEPs, and stdlib contributions (collections, itertools, dataclasses).

punt-labs/z-spec · 32 tokens