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 Dragoon0x/taste-skills --skill consumption-disciplinegit clone --depth 1 https://github.com/Dragoon0x/taste-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/dragoon0x/taste-skills/consumption-discipline)<a href="https://agentmods.dev/skills/dragoon0x/taste-skills/consumption-discipline"><img src="https://agentmods.dev/badge/skills/dragoon0x/taste-skills/consumption-discipline/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/dragoon0x/taste-skills/consumption-discipline"><img src="https://agentmods.dev/badge/skills/dragoon0x/taste-skills/consumption-discipline.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 | $0.00058 | $0.00632 |
| Opus 5 | $0.00029 | $0.00316 |
| Sonnet 5 | $0.00012 | $0.00126 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
consumption-discipline 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 11d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consumption Discipline
Great taste is built through relentless exposure. You can't taste what you've never tasted.
How to use
/consumption-disciplineApply structured consumption constraints to professional development in this conversation.
Constraints
The Core Rule
- MUST consume more than you create. The ratio matters. If you're only making and never absorbing, your taste ceiling is whatever you already know.
- MUST consume actively, not passively. Scrolling Dribbble is passive. Spending 10 minutes deconstructing one design is active.
- MUST consume across domains. Design is the obvious input. Architecture, film, food plating, fashion, music production, editorial print, industrial design are the non-obvious inputs that widen your range.
- NEVER consume from a single source. If all your references come from one platform, one country, or one decade, your taste has a monoculture problem.
Consumption Structure
- MUST balance breadth and depth: wide exposure builds range, deep study builds understanding
- Breadth: 3-5 new products, spaces, or artifacts per week from domains you don't normally visit
- Depth: 1 extended study per week (30+ minutes deconstructing a single piece of work)
- SHOULD schedule consumption like you schedule workouts. It doesn't happen on its own.
- SHOULD track what you consume. A simple log reveals your blind spots over time.
What to Consume
- Screen: products you'd never use, from markets you don't serve, in languages you don't speak
- Physical: museum exhibitions, retail stores, hotel lobbies, restaurant interiors, packaging
- Temporal: work from the 1950s, 1970s, 1990s. Design principles don't expire. Understanding how the same problems were solved in different eras gives you range no amount of contemporary exposure can.
- Cultural: design from Japan, Brazil, Netherlands, Nigeria, India, Switzerland. Every design culture has principles the others haven't discovered.
- Adjacent: film editing, music composition, food presentation, fashion construction, architecture. The principles transfer. The aesthetics don't have to.
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.
- 11d ago First seen · 47 lines · 58 tokens per session scan A c4985b2e2924
consumption-discipline is a skill published in the GitHub repository Dragoon0x/taste-skills (4 stars, last pushed 6mo ago), licensed MIT. It adds 58 tokens to every session and 632 once invoked, about $0.0003 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
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
motion-graphics
Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s…
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
goose-graphics
Portable visual skill pack for the Agent Skills ecosystem (Claude Code, Claude Desktop, Claude Cowork, Claude Design, Goose, Cursor, Codex). Discovers community-published styles + formats via the gooseworks CLI, runs an extract-style workflow on reference images, and exports rendered PNGs via Playwright.
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…
create-imessage-mockup
Render pixel-accurate iMessage screenshot mockups (DM or group) from a thread JSON. Supports minimal, with-keyboard, and full iPhone 15 Pro frame variants. Outputs HTML + PNG.