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 somnus0x/agt-skill-pack --skill product-tastegit clone --depth 1 https://github.com/somnus0x/agt-skill-packWrote 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/somnus0x/agt-skill-pack/product-taste)<a href="https://agentmods.dev/skills/somnus0x/agt-skill-pack/product-taste"><img src="https://agentmods.dev/badge/skills/somnus0x/agt-skill-pack/product-taste/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/somnus0x/agt-skill-pack/product-taste"><img src="https://agentmods.dev/badge/skills/somnus0x/agt-skill-pack/product-taste.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 | $0.00044 | $0.01062 |
| Opus 5.5 | $0.00018 | $0.00425 |
| Sonnet 5.5 | $0.00009 | $0.00212 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
product-taste 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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Taste — What to Build, What to Cut
Taste isn't opinion. It's pattern recognition compressed into instinct. This skill builds product taste by forcing structured evaluation before enthusiasm or inertia makes the decision for you.
The Taste Test
When evaluating a feature, idea, or product decision — run it through five filters in order. Stop at the first filter that kills it.
Filter 1: Who suffers without this?
Name the specific person. Not "users" — one person with a context and a pain. If you can't name them, the feature is a solution looking for a problem.
Bad: "Users would benefit from group functionality." Good: "A user who found a hot take on Twitter wants to share it with friends, but can't because the flow only supports solo use."
If the suffering is hypothetical or vague — kill the feature.
Filter 2: What does this replace?
Every feature competes with doing nothing. The user's current workaround — however ugly — is working. What are they doing today instead? How painful is that workaround?
Rate the workaround pain:
- Unbearable → Build it
- Annoying → Maybe
- Fine → Don't build it
If the workaround is tolerable — the feature is a vitamin, not a painkiller. Vitamins lose to painkillers every time in early-stage products.
Filter 3: Does this make the core loop stronger?
Every product has one core loop. Define yours first (e.g., discover → create → engage → resolve). Every feature should make one step of this loop faster, easier, or more frequent.
If the feature doesn't touch the core loop — it's a distraction. A settings page, an analytics dashboard, a profile customization system — none of these make more core actions happen.
Ask: "Does this make someone do the core action faster?" If no — cut it or defer it.
Filter 4: What's the cost of being right?
Assume the feature works perfectly. Users love it. Now what?
- Does it increase surface area you have to maintain?
- Does it add new state to manage?
- Does it create a new failure mode?
- Does it split attention across two things instead of focusing on one?
What ships with it
3 files 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.
- 1mo ago First seen · 105 lines · 44 tokens per session scan A b3ba4af23cd0
product-taste is a skill published in the GitHub repository somnus0x/agt-skill-pack (74 stars, last pushed 18d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,062 once invoked, about $0.0002 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…