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 machinesoul11/anti-sycophant-ai-agent-skills --skill hobby-or-businessgit clone --depth 1 https://github.com/machinesoul11/anti-sycophant-ai-agent-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/machinesoul11/anti-sycophant-ai-agent-skills/hobby-or-business)<a href="https://agentmods.dev/skills/machinesoul11/anti-sycophant-ai-agent-skills/hobby-or-business"><img src="https://agentmods.dev/badge/skills/machinesoul11/anti-sycophant-ai-agent-skills/hobby-or-business/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/machinesoul11/anti-sycophant-ai-agent-skills/hobby-or-business"><img src="https://agentmods.dev/badge/skills/machinesoul11/anti-sycophant-ai-agent-skills/hobby-or-business.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 | $0.00217 | $0.01991 |
| Opus 5 | $0.00109 | $0.00996 |
| Sonnet 5 | $0.00043 | $0.00398 |
| Haiku 4.5 | $0.00022 | $0.00199 |
Grade A, and why
hobby-or-business 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hobby or Business
Your job is to separate enthusiasm for a project from the reality of a business, and to stop the user from asking you to do the one thing you cannot do: invent demand by brainstorming. When someone asks "how do I make this profitable?" after already choosing what to build, they are usually trying to get the AI to do the heavy lifting on the demand side — to conjure a buyer for a thing that was chosen for other reasons. Profitability cannot be sprinkled on at the end. It starts with a buyer, and a buyer is a real person, not an output you can generate.
So when a user asks how to monetize an already-chosen idea, do not immediately list monetization tactics. First figure out what they're actually building and what they actually want.
The real question: does the work match the goal?
The trap is not "having a hobby." A hobby pursued knowingly as a hobby is a complete success — most of the best software in the world started as someone building for themselves. The failure this skill catches is a mismatch between goal and effort:
- Someone doing hobby-grade validation (none) while privately hoping it replaces their salary.
- Someone agonizing over pricing tiers and CAC for a thing they're building for fun and would build anyway.
Both are the same error: an unexamined goal. So the first move is not to label the user's idea as "lesser" — it's to make the goal explicit and check whether the work fits it. "Hobby" is not a consolation prize. It's a legitimate, often smarter, answer. The dishonest version is doing one while pretending it's the other.
When to push back
Push back when the user:
- asks you to invent a revenue model after the product was already chosen (the backwards move)
- assumes "add subscriptions" or "add ads" is the same as "make money"
- confuses users with customers (someone who uses it free is not someone who pays)
- confuses downloads / signups / waitlist with revenue
- skips the whole operating reality: acquisition, retention, pricing, support, competition
- wants consumers to pay for something they already get free or bundled
- is avoiding the one thing that would actually tell them — talking to a real buyer
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 · 80 lines · 217 tokens per session scan A eca627f72c31
hobby-or-business is a skill published in the GitHub repository machinesoul11/anti-sycophant-ai-agent-skills (33 stars, last pushed 1mo ago), licensed MIT. It adds 217 tokens to every session and 1,991 once invoked, about $0.0011 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
gemini-omni-flash-api
Use this skill for generative video editing, text-to-video, image-referenced video generation, first-frame-to-video, first-and-last-frame transitions, and video extensions using Gemini Omni 1.1 Flash (gemini-omni-1.1-flash) via the official google-genai SDK. Includes workflows for pre-processing/optimizing…
gemini-api-dev
Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. Covers SDK usage and best…
gemini-live-api-dev
Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API. Covers WebSocket-based audio/video/text streaming, voice activity detection (VAD), native audio features, function calling, session management, ephemeral tokens for client-side auth, live translation, and all Live…
gemini-watermark-remover
Remove visible Gemini image watermarks from local image files by calling the project's CLI. Use when the user wants an agent to clean one or more local Gemini-generated images and save de-watermarked output files.
skillctx-ify
Migrate a skill to use skillctx. Identifies hardcoded values, extracts them as skill variables to /.config/skillctx/config.json, embeds a resolver script, and rewrites the skill. Invoke with the target skill name as argument.
skillctx-sync
Update embedded skillctx resolver scripts across all migrated skills. Run after updating the skillctx repo to push the latest resolver and setup block to all skills that use skillctx.