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 agentmods add skills/szoloth/skill-pack/tastenpx skills add SZoloth/skill-pack --skill tastegit clone --depth 1 https://github.com/SZoloth/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/szoloth/skill-pack/taste)<a href="https://agentmods.dev/skills/szoloth/skill-pack/taste"><img src="https://agentmods.dev/badge/skills/szoloth/skill-pack/taste.svg" alt="Measured on agentmods" 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 | $0.00151 | $0.01338 |
| Opus 5 | $0.00076 | $0.00669 |
| Sonnet 5 | $0.00030 | $0.00268 |
| Haiku 4.5 | $0.00015 | $0.00134 |
Grade A, and why
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 4d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taste
Taste is domain-grounded judgment applied during creation. It is not a polish pass and not a slop-removal checklist. It is the difference between output that is merely competent and output that reflects an actual understanding of what practitioners in a field consider good.
The failure mode this skill corrects is straightforward: agents produce work that is technically complete but obviously generated. The information may be correct, but the judgment is absent. Equal weight goes to unequal ideas. Structure appears because templates exist, not because the content needs it. Details stay in because they were available, not because they matter.
This skill fixes that by requiring you to understand the domain before you touch the work.
Grounding Requirement
Before creating anything, establish a domain model. The depth required depends on how far the domain is from your reliable knowledge.
If you know the domain cold:
- State the assumptions behind the quality bar and move.
- Do not perform research theater.
If you know the domain but not the current state:
- Research first.
- Look at current exemplars, docs, or conventions.
- A grounded first draft is better than an ungrounded third draft.
If the domain is unfamiliar or specialized:
- Stop and learn before creating.
- Read exemplars from practitioners, not tutorials about the domain.
- Understand what people in the field care about and what they treat as background.
The grounding step should produce three things:
- The quality bar: what good looks like here, with specific reference points.
- The assumed knowledge: what the audience already knows and will not tolerate having explained back to them.
- The attention budget: where practitioners spend care and where they do not.
Skip grounding only when the domain is obvious and you are certain. When uncertain, ground.
Core Principles
1. Exclusion is the primary act of taste
The first judgment is what to leave out. This is only possible if you understand the function of the material you're cutting. Taste without domain knowledge is just confidence.
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.
- 4d ago First seen · 127 lines · 151 tokens per session scan A e10aef580d7a
taste is a skill published in the GitHub repository SZoloth/skill-pack (14 stars, last pushed 5mo ago), licensed MIT. It adds 151 tokens to every session and 1,338 once invoked, about $0.0008 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
narrative-text-visualization
Generate structured narrative text visualizations from data using T8 Syntax. Use when users want to create data interpretation reports, summaries, or structured articles with semantic entity annotations. T8 is designed for unstructured data visualization where T stands for Text and 8 represents a byte of 8 bits…
gpt-vis
推荐并生成合适的数据可视化图表，使用 GPT-Vis 库。支持两种输出模式：（1）语法模式——生成 Syntax 或 JSON 配置；（2）代码模式——生成完整的运行代码。支持 26 种图表类型。.
antv-x6-editor
Use this skill whenever the user wants to create, customize, or troubleshoot X6 v3 graph editor diagrams. Triggers include: any mention of 'X6', 'antv x6', '@antv/x6', 'X6 editor', 'X6 图编辑', '流程图', 'DAG', 'ER图', '实体关系图', '血缘图', '组织架构图', 'UML类图', 'flowchart', 'DAG diagram', 'ER diagram', 'lineage graph', 'org chart'…
infographic-creator
Create beautiful infographics based on given text content. Use when users request to create infographics.
antv-g2-chart
Use this skill whenever the user wants to create, customize, or troubleshoot G2 v5 chart visualizations. Triggers include: any mention of 'G2', 'antv g2', '@antv/g2', 'G2 chart', 'G2 可视化', or requests to produce charts like bar charts (柱状图), line charts (折线图), pie charts (饼图), scatter plots (散点图), area charts (面积图)…
antv-g6-graph
Use this skill whenever the user wants to create, customize, or troubleshoot G6 v5 graph/network visualizations. Triggers include: any mention of 'G6', 'antv g6', '@antv/g6', 'G6 graph', 'G6 图', '网络图', '关系图', '拓扑图', '树形图', '流程图', '思维导图', '鱼骨图', '力导向图', 'force graph', 'network visualization', 'node-edge diagram'…