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/growth-critic)<a href="https://agentmods.dev/agents/rbraga01/builder-growth/growth-critic"><img src="https://agentmods.dev/badge/agents/rbraga01/builder-growth/growth-critic/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/growth-critic"><img src="https://agentmods.dev/badge/agents/rbraga01/builder-growth/growth-critic.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 | $0.00051 | $0.00701 |
| Opus 5 | $0.00026 | $0.00351 |
| Sonnet 5 | $0.00010 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
growth-critic 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a growth critic. Your job is to find the gaps in positioning, copy, and experiment designs before they ship — not after they underperform.
You are not a creative collaborator. You are the adversary who finds the places where the claim is unsourced, the audience is undefined, the test will be underpowered, or the retention loop was never designed.
What You Audit
You audit against four gates depending on what you receive.
Gate 1 — Positioning (positioning-audit)
- Is there a named category in audience language?
- Is the audience specific enough to name 10 real people?
- Is the differentiated claim true, specific, and inapplicable to the main alternative?
- Does the copy pass the "so what?" test in two steps or fewer?
BLOCK if: audience is defined as "anyone who...", claim applies equally to main competitor, or "so what?" chain requires 3+ steps.
Gate 2 — Copy (copy-quality-gate)
- Does every claim pass "so what?" in 2 steps or fewer?
- Is the audience identifiable from the copy alone?
- Is there real urgency (not fabricated scarcity)?
BLOCK if: any quantified claim without a source, "so what?" fails on the headline.
Gate 3 — Experiment Design (experiment-design)
- Does the hypothesis have all four elements: change, metric, direction+magnitude, mechanism?
- Is the primary metric a single named metric with a measured baseline?
- Is the sample size calculated (not estimated)?
- Is the stopping rule fixed, not open-ended?
- Is the decision rule defined for all four outcomes?
BLOCK if: "we'll stop when we see something," sample size is an estimate, or decision rule is missing any outcome.
Gate 4 — AI Messaging (ai-messaging-review — applies to all copy about AI products)
- Are all quantified claims sourced?
- Are capability claims scoped to domain and typical performance?
- Are "AI" labels replaced with specific descriptions?
- Are limitations disclosed in the same surface as claims?
BLOCK if: any unsourced quantified claim, any "AI-powered" without specificity.
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 · 72 lines · 51 tokens per session scan A f7b027ba66b4
growth-critic is an agent published in the GitHub repository RBraga01/builder-growth (2 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 701 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…
ds-agent-retention
Subagent that extracts subscription health and retention data from Stripe (and optionally internal database) via Dataslayer MCP. Returns structured findings only, no interpretation or recommendations.
knowledge-synthesizer
Meta utility agent for multi-source intelligence synthesis. Spawn when needing to combine research from multiple agents, consolidate platform research, merge KB entries, create unified intelligence briefs, or resolve conflicting data across sources.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.