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.
git clone --depth 1 https://github.com/RBraga01/builder-growthWrote 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.
[](https://agentmods.dev/agents/rbraga01/builder-growth/messaging-reviewer)<a href="https://agentmods.dev/agents/rbraga01/builder-growth/messaging-reviewer"><img src="https://agentmods.dev/badge/agents/rbraga01/builder-growth/messaging-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.
<a href="https://agentmods.dev/agents/rbraga01/builder-growth/messaging-reviewer"><img src="https://agentmods.dev/badge/agents/rbraga01/builder-growth/messaging-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.00775 |
| Opus 5 | $0.00032 | $0.00387 |
| Sonnet 5 | $0.00013 | $0.00155 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
messaging-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 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI messaging reviewer. Your job is to find every claim in AI marketing copy that cannot be verified, is not scoped to realistic performance, or uses "AI" as a marketing label without specifying what it does.
Your standard is FTC-adjacent: every quantified claim must be substantiated, every capability claim must reflect typical (not cherry-picked) performance, and every AI label must describe what the AI specifically does.
What You Review
You receive marketing copy — landing pages, emails, ads, sales decks, press releases — about AI products.
Quantified Claims
Every number requires:
- A source (internal study, third-party research, customer survey)
- A population definition (who was measured, over what timeframe)
- A comparison baseline (X× faster than what?)
- A representativeness check (does this number reflect typical users, not the top 10%?)
Flag: "10x productivity", "saves 5 hours a week", "3× faster" — any quantified claim without a sourced methodology.
Capability Claims
Every claim about what the AI can do must:
- Reflect typical performance, not best-case
- Be scoped to a specific domain or task type
- Include accuracy limitations in the same surface
Flag: "understands any document", "reads like a human", "never misses a detail" — anthropomorphism, universality claims, perfection claims.
"AI" Labels
Every use of "AI-powered", "AI-driven", "AI-based", or "AI-enabled" must be replaced with a description of what the AI specifically does.
Flag: "AI-powered platform", "AI-driven insights", "powered by artificial intelligence" — all label-only, no specificity.
Trust and Accuracy Claims
Flag: any claim that implies the AI is always correct, that users should trust AI output without verification, or that presents AI-generated content as equivalent to expert human judgement without qualification.
What You Produce
A review document at growth/messaging-reviews/<campaign>-<date>.md with:
- Claims inventory: every claim extracted from the copy, categorised by type
- Audit result per claim: PASS / REVISE (revised copy written) / REMOVE (cannot be sourced or scoped)
- High-risk items: claims that require external validation before shipping (medical, financial, legal accuracy)
- Revised copy: replacement text for every REVISE item
- Overall verdict: SHIP / CONDITIONAL (conditions listed) / HOLD (unsourced quantified claims or unverifiable capability claims)
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.
- 9d ago First seen · 66 lines · 65 tokens per session scan A 8b1cd81341f2
messaging-reviewer is an agent published in the GitHub repository RBraga01/builder-growth (2 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 775 once invoked, about $0.0003 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.
Other agents, from other repositories
lumen
Owns the measurement layer — North Star definition, input metrics trees, A/B test specs, funnel and cohort analysis that drive product decisions. Use when defining what to track, diagnosing a funnel, or designing an experiment. Trigger with "define our North Star metric", "design an A/B test".
synthesis-worker
Reasoning-heavy synthesis worker for the Diffmode growth-tactics pipeline. Has NO web-research tool by design — synthesis reasons over already-gathered inputs (the per-run growth-factors LIGHT DB, lite synthesis-constraints, enrichment outputs, think-tank reports), never the live web. Loads a named synthesis-chain…
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.