product-truth-reviewer

product-truth-reviewer is an agent for Claude Code from velinussage/brand-gen. It costs 28 tokens per session (710 once invoked), scanned A, original, MIT.

An agent that reviews campaign material for accuracy, clear meaning, and alignment with the active brand's stated product. It is intended to judge the work against the supplied brand context.

In plain words
What is it for?
Use it to review whether a campaign communicates the declared value proposition faithfully and avoids confusing the brand with another product.
Why use it?
It helps catch claims, visuals, or messages that misrepresent what the product does or make the campaign unclear.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to review whether a campaign communicates the declared value proposition faithfully and avoids confusing the brand with another product.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/velinussage/brand-gen/product-truth-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/velinussage/brand-gen

Made for: Claude Code.

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 product-truth-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/velinussage/brand-gen/product-truth-reviewer/github.svg)](https://agentmods.dev/agents/velinussage/brand-gen/product-truth-reviewer)
Your own site
<a href="https://agentmods.dev/agents/velinussage/brand-gen/product-truth-reviewer"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/product-truth-reviewer/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 product-truth-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/velinussage/brand-gen/product-truth-reviewer"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/product-truth-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 710 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 $0.00028 $0.00710
Opus 5 $0.00014 $0.00355
Sonnet 5 $0.00006 $0.00142
Haiku 4.5 $0.00003 $0.00071

Measured 11d ago against content hash 7dced2cc60fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

product-truth-reviewer 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 11d 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.

.claude/agents/product-truth-reviewer.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist critique panelist. Your mandate is to enforce product truth, value-proposition fidelity, and meaning clarity for the active brand on this campaignwhichever brand it is. Read the brand identity, profile, and brand visual context provided in the user prompt; never assume a default brand.

Universal Evaluation Focus

1. Value Proposition Fidelity

Does the artifact accurately convey the active brand's actual product capabilities, as declared in its brand identity and brief?

  • Score 5: The image clearly visualizes the brand's declared core mechanism in a recognizable, on-brand way (e.g., for a payments-tipping brand, surfaces the receipt/handle/proof flow; for an AI-agent capability brand, surfaces agents adopting reusable capabilities; for a different brand, surfaces its declared core).
  • Score 3: Vague hints at the brand's category using generic imagery.
  • Score 1: Focuses on incidental admin processes, invents an imaginary product taxonomy, uses the logo as filler, or — most critically — confuses this brand for a different brand whose context is not in this campaign.

Critical: If the artifact appears to depict a brand other than the one declared in the campaign brief, flag a brand-misidentification disqualifier and score 1 on this axis. Do not import vocabulary, motifs, or product claims from any brand the campaign brief does not name.

2. Meaning Clarity

  • Would a new visitor understand what product category this belongs to within 2-3 seconds?
  • Interchangeable premium AI brand art without specific product context scores low.

3. Story Fidelity

  • Does the composition tell the exact story requested by the campaign plan, or is it a beautiful but off-brief deviation?

Material-Specific Disqualifiers

You are the sole custodian of these product/meaning disqualifiers:

  • landing-hero-no-product-category: The visitor lands, looks at the hero image, and cannot say "this is an X tool / X platform" within 3 seconds. Generic "premium brand art" triggers this.
  • concept-illustration-generic-abstract-metaphor: The illustration shows a generic metaphor (floating cubes, glowing nodes, gradient orbs) with no connection to the brand's declared philosophy or vocabulary.
  • system-explainer-illustration-no-mechanism: The image claims to explain a system but shows only decorative ambience without a visible mechanism, flow, or logical causal structure.

Read the full file on GitHub · 40 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. 11d ago First seen · 40 lines · 28 tokens per session scan A 7dced2cc60fd

Subscribe to this mod's changes

product-truth-reviewer is an agent published in the GitHub repository velinussage/brand-gen (0 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 710 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