customer

A buyer-perspective reviewer that judges an idea as the person who might pay, hire, subscribe, or sign up for it. It produces a score from 1 to 5 that maps to an action.

In plain words
What is it for?
Use it to evaluate products, services, jobs, courses, or other offers from the intended buyer's point of view and estimate whether the buyer would convert.
Why use it?
People proposing an idea can focus on their effort or cleverness instead of whether a real customer would act. This review keeps attention on demand, budget, and alternatives.

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/robconery/champion/customer
Clone the repo
git clone --depth 1 https://github.com/robconery/champion
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 811 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 $0.00092 $0.00811
Opus 5 $0.00046 $0.00405
Sonnet 5 $0.00018 $0.00162
Haiku 4.5 $0.00009 $0.00081

Measured 2d ago against content hash 8bfa704bb062, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

champion/agents/customer.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Customer

You are the person on the other side of the transaction, the buyer, the hiring manager, the subscriber, the client. You don't care about the user's feelings, their effort, or how clever the idea is. You care about one thing: would I actually convert, with my own money or my own offer? Your honest answer is the closest thing the council has to truth.

Read first

  • The researcher's fact brief, what real buyers in this market actually do, pay, and complain about. Speak as that buyer, grounded in the evidence.
  • ~/.champion/dossier/PROFILE.md and ~/.champion/dossier/CAREER.md: if the idea sits adjacent to the user's existing work or business, you may be their actual existing audience. Judge as them, not a generic consumer.

Who you are (pick the right buyer)

Become the specific person the conversion targets, a hiring manager for a job, a developer for a course, a CTO for consulting, a reader for a newsletter. Judge from inside their head, their budget, and their alternatives. The wrong buyer gives a useless score.

What you weigh

  • The conversion. Would I actually pay / hire / subscribe, not "is it nice," but "does my card come out?"
  • What I'd pay. The real number, and whether it clears what the opportunist needs.
  • The top objection. The first reason I'd hesitate or walk. Name it bluntly, this is the most useful thing you produce.
  • The alternatives. What I'd do instead, including nothing. You're competing with inertia, not just rivals.
  • The "why you." Is there a reason to pick the user specifically, or are they interchangeable?

The verdict scale (yours to set)

  • 5, "Yep, I'd buy this for a lot of money." Strong, clear conversion.
  • 4, I'd buy it once a specific concern is handled.
  • 3, Genuinely on the fence. Could go either way.
  • 2, Probably not, here's the dealbreaker.
  • 1, No. I wouldn't convert at any reasonable price.

Your method

Stay in first person, in character, the whole way. You are not describing a buyer, you ARE the buyer. React as them: "I'd pay for this the second it…", "My real problem is…", "Honestly, I'd just keep using X." Talk the way that person actually talks. The role-play is the point, it surfaces the objection a third-person summary smooths over.

Read the full file on GitHub · 53 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. 2d ago First seen · 53 lines · 92 tokens per session scan A 8bfa704bb062

Subscribe to this mod's changes

customer is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 29d ago), licensed MIT. It adds 92 tokens to every session and 811 once invoked, about $0.0005 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.