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/jangles-byte/atelier/design-directionnpx skills add jangles-byte/atelier --skill design-directiongit clone --depth 1 https://github.com/jangles-byte/atelierWrote 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/jangles-byte/atelier/design-direction)<a href="https://agentmods.dev/skills/jangles-byte/atelier/design-direction"><img src="https://agentmods.dev/badge/skills/jangles-byte/atelier/design-direction.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 | $0.00120 | $0.00590 |
| Opus 5 | $0.00060 | $0.00295 |
| Sonnet 5 | $0.00024 | $0.00118 |
| Haiku 4.5 | $0.00012 | $0.00059 |
Grade A, and why
design-direction 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 3d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Direction
Generic output happens when implementation starts before intent exists. This skill forces the intent step: a short, written design philosophy that commits to one aesthetic point of view — and names what it is not — before a single pixel exists.
Workflow
- Interrogate the brief — answer the five questions in references/interrogation.md. If the user's request doesn't answer them, infer defensible answers from context and state your assumptions; do not stall on questions when the user isn't available.
- Write the philosophy — a named direction plus 4–6 tight paragraphs, using the
format in references/philosophy-format.md.
Write it into the project (e.g.
DESIGN.md) or state it in full before implementing. - Pick a point of view — choose or blend a direction from references/aesthetic-vocabularies.md, and check the result against references/anti-generic.md (the catalog of default-AI tells to avoid).
- Then implement — loading the other Atelier skills (
color,typography-and-layout,motion) as the work requires them. - Render, critique, iterate — never ship a visual without rendering the real
result and running the
critiqueskill on it.
Which reference to load
| Situation | Load |
|---|---|
| Starting any visual work | references/interrogation.md then references/philosophy-format.md |
| Choosing/naming an aesthetic | references/aesthetic-vocabularies.md |
| Work is drifting generic, or reviewing for genericism | references/anti-generic.md |
The one rule
Every project gets one signature move — a single distinctive decision (a color no template uses, an unusual type pairing, a bold grid break, a characteristic motion) that someone could describe from memory. If nothing about the design is describable, the direction step failed. Go back to step 2.
What ships with it
4 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.
- 3d ago First seen · 44 lines · 120 tokens per session scan A 26472d90e65f
design-direction is a skill published in the GitHub repository jangles-byte/atelier (2 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 590 once invoked, about $0.0006 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
sheleg-design
Use when deciding how something LOOKS or MOVES — cinematic landing pages and hero sections, particle/WebGL backgrounds, scroll-linked or scrubbed motion, layers that drift, dashboards, admin or internal tools, mobile screens, chat or agent interfaces, tokens, themes, palettes, typography and the Figma border. Triggers…
html-ppt-zhangzara-biennale-yellow
A curatorial deck for a contemporary art biennale — the thesis, the rooms, the works, and the visitor journey. Built as a decision-grade design craft deck for museum board, curators.
html-ppt-zhangzara-block-frame
Rescuing a messy startup deck into a board-grade system — the diagnosis, the page grammar, and the rebuilt proof pages. Built as a decision-grade design craft deck for founders, exec presenter.
figma
Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), connector-assisted motion when available, and shaders from a connector or native export. Use when the user pastes a figma.com link…
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…
add-component
Add a SwiftUI component from ShipSwift. Use when the user says "add component", "add a view", "add X view", "I need a chart", "add animation", or wants a specific UI element.