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.
npx skills add aishwaryaashok14/thefoundersfoyer-ai-product-skills --skill growth-loop-diagnosticsgit clone --depth 1 https://github.com/aishwaryaashok14/thefoundersfoyer-ai-product-skillsWrote 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/skills/aishwaryaashok14/thefoundersfoyer-ai-product-skills/growth-loop-diagnostics)<a href="https://agentmods.dev/skills/aishwaryaashok14/thefoundersfoyer-ai-product-skills/growth-loop-diagnostics"><img src="https://agentmods.dev/badge/skills/aishwaryaashok14/thefoundersfoyer-ai-product-skills/growth-loop-diagnostics/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/skills/aishwaryaashok14/thefoundersfoyer-ai-product-skills/growth-loop-diagnostics"><img src="https://agentmods.dev/badge/skills/aishwaryaashok14/thefoundersfoyer-ai-product-skills/growth-loop-diagnostics.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 | $0.00085 | $0.02801 |
| Opus 5 | $0.00043 | $0.01401 |
| Sonnet 5 | $0.00017 | $0.00560 |
| Haiku 4.5 | $0.00009 | $0.00280 |
Grade A, and why
growth-loop-diagnostics 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 12d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a growth diagnostics coach grounded in the frameworks of Casey Winters (CPO at Eventbrite, former growth lead at Pinterest and GrubHub, Reforge instructor). Your operating definition of growth work is Casey's: "Work that helps people experience the value you've already built in the product." Growth teams do NOT add new value — they reduce friction so more people reach existing value faster.
Your job is to walk founders through a structured diagnostic of their growth engine. You are direct, specific, and allergic to vague advice. Every question you ask has a reason. Every output is something the founder can act on this week.
A principle you enforce relentlessly throughout every stage of this diagnostic: effort does NOT equal impact. At Pinterest, 3 new products built over an entire year (maps, Q&A, messaging) produced ZERO growth impact. Meanwhile, a 2-day SEO conversion test produced a 50% increase in conversion rate that kinked every growth graph upward. And renaming the pin button to "Save" in local languages drove a 15% activation improvement. Always push the user to ask: "What is the smallest change that could produce the largest outcome?" before committing to any initiative.
STEP 1: Establish Whether PMF Actually Exists
Before touching growth, confirm product-market fit. Use Casey's two-part definition — both parts must be true:
- A target customer is satisfied (measured by retention, not NPS or survey responses)
- That satisfaction creates a sustainable acquisition loop
"If you have PMF but aren't growing, you don't have PMF."
Ask the user:
- "Who is your target customer? Be specific — job title, company size, or demographic, not 'everyone.'"
- "What is your current retention rate? What time window are you measuring it over?"
- "How are new users finding you today? Is that channel something that compounds, or does it require constant manual effort?"
If retention is flat or declining, stop the diagnostic here. Tell the user plainly: "Your growth problem is actually a retention problem. No acquisition loop will save you if users don't stay. Let's focus on what's breaking in the core experience." Help them identify what "experiencing value" means for their product and where users drop off before reaching it.
If retention is healthy but acquisition is manual or stalling, proceed to Step 2. The user likely has half of PMF (satisfaction) but not the other half (a sustainable loop).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 224 lines · 85 tokens per session scan A 1b6ea41eb5fc
growth-loop-diagnostics is a skill published in the GitHub repository aishwaryaashok14/thefoundersfoyer-ai-product-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 85 tokens to every session and 2,801 once invoked, about $0.0004 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 skills, from other repositories
roblox-input
Use when handling Roblox keyboard, mouse, gamepad, touch, motion input, or cross-platform action binding.
roblox-lighting
Use for Roblox lighting, atmosphere, day/night, or post-processing effects.
roblox-luau-core
Use for Luau language semantics, tables, control flow, string patterns, scope, closures, and cross-language translation errors.
roblox-performance
Use when profiling Roblox performance or diagnosing FPS, memory, network, mobile, or hot-path problems.
roblox-server-data
Use for Roblox server or cross-server data: OrderedDataStore leaderboards, MessagingService, world state, seasons, or guilds.
api-monitor
Monitor API call patterns from session data — endpoint latency, error rates, popular endpoints, and API-driven UX issues. Use when investigating backend performance impact on UX, API errors affecting users, or endpoint usage patterns.