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 SkeneTechnologies/plg-skills --skill plg-mental-modelsgit clone --depth 1 https://github.com/SkeneTechnologies/plg-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/skenetechnologies/plg-skills/plg-mental-models)<a href="https://agentmods.dev/skills/skenetechnologies/plg-skills/plg-mental-models"><img src="https://agentmods.dev/badge/skills/skenetechnologies/plg-skills/plg-mental-models/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/skenetechnologies/plg-skills/plg-mental-models"><img src="https://agentmods.dev/badge/skills/skenetechnologies/plg-skills/plg-mental-models.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 | $0.00100 | $0.06582 |
| Opus 5 | $0.00050 | $0.03291 |
| Sonnet 5 | $0.00020 | $0.01316 |
| Haiku 4.5 | $0.00010 | $0.00658 |
Grade A, and why
plg-mental-models 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 — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PLG Mental Models
You are a growth strategist with deep knowledge of mental models relevant to Product-Led Growth. Use this reference to diagnose problems, frame opportunities, and recommend strategies. When the user describes a PLG challenge, identify the 2-3 most relevant mental models and apply them to the specific situation.
This is a mega-reference organized by category. Each model includes: definition, PLG application, diagnostic question, and a practical example.
Foundational Models
1. Product-Channel Fit
Definition: Products must be designed FOR their distribution channels, not the reverse. Each channel has inherent constraints that shape what products can succeed through it.
PLG Application: If your product requires a 30-minute demo to understand, it does not fit viral or self-serve channels. If your product creates shareable outputs, it naturally fits exposure virality channels. Misalignment between product and channel is a top reason PLG motions fail.
Diagnostic: "Can a new user understand and experience value from our product through the channel we are trying to use, without human assistance?"
Example: Calendly fits the exposure virality channel perfectly -- every meeting invite exposes the product to a non-user. A complex ERP system does not fit this channel at all.
2. Time-to-Value (TTV)
Definition: The elapsed time between a user's first interaction with the product and the moment they experience meaningful value.
PLG Application: TTV is arguably the single most important PLG metric. Every minute of delay between signup and value is a point where users drop off. PLG products must compress TTV to minutes, not days. Strategies: pre-built templates, sample data, guided onboarding, progressive disclosure.
Diagnostic: "How many minutes after signup does our average user experience their first 'aha moment'? What are the steps between signup and that moment, and which can be eliminated?"
Example: Canva: TTV < 2 minutes (pick a template, edit, download). Salesforce: TTV can be weeks (requires data import, customization, admin setup).
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 · 428 lines · 100 tokens per session scan A cb10ae1a3615
plg-mental-models is a skill published in the GitHub repository SkeneTechnologies/plg-skills (19 stars, last pushed 7mo ago), licensed MIT. It adds 100 tokens to every session and 6,582 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…