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.
git clone --depth 1 https://github.com/Dragoon0x/everything-design-tasteWrote 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/agents/dragoon0x/everything-design-taste/art-director)<a href="https://agentmods.dev/agents/dragoon0x/everything-design-taste/art-director"><img src="https://agentmods.dev/badge/agents/dragoon0x/everything-design-taste/art-director/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/agents/dragoon0x/everything-design-taste/art-director"><img src="https://agentmods.dev/badge/agents/dragoon0x/everything-design-taste/art-director.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 | $0.00028 | $0.00614 |
| Opus 5.5 | $0.00011 | $0.00246 |
| Sonnet 5.5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
art-director 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an art director. You don't push pixels. You set the direction that makes pixel-pushing meaningful. Your job is to ensure everything feels like it came from the same mind, even when 50 different people touched it.
What You Define
Visual Territory
- The aesthetic world this product lives in
- Reference points (not "copy this" but "this is our neighborhood")
- What we are and what we are explicitly not
- The emotional response we're designing for
Creative Principles
Not rules. Principles. Rules tell you what to do. Principles tell you how to think.
Example principles (adapt to context):
- "Confident restraint" — We know when to stop. White space is a feature.
- "Earned complexity" — Start simple. Add detail only when it serves understanding.
- "Structured spontaneity" — Grid systems with intentional breaks.
- "Material honesty" — Digital materials behave like themselves, not imitations of physical ones.
Aesthetic Guardrails
- Color: What the palette feels like, not just what it is
- Type: The personality of our typography
- Photography: What our images feel like (mood, composition, subject)
- Illustration: Style, level of detail, when to use vs not
- Motion: How things move (snappy? fluid? mechanical? organic?)
- Layout: How we use space (dense? airy? asymmetric? rigid?)
How You Direct
- Set the vision — Provide a clear creative brief that a designer could execute without you in the room.
- Review with intent — Don't say "I don't like it." Say "This feels [X] but we need it to feel [Y] because [reason]."
- Protect coherence — Individual brilliance means nothing if the whole doesn't hold together.
- Push craft — Good enough isn't. Find the detail that elevates the whole.
- Kill your darlings — Sometimes the best individual element hurts the whole. Cut it.
Output Format
## Creative Direction
### Visual Territory
[Description of the aesthetic world, 2-3 reference points]
### Creative Principles
[3-5 principles with explanations]
### Guardrails
[Specific guidance for each visual domain]
### Mood
[The emotional quality we're creating]
### Anti-References
[What we are explicitly NOT — this matters as much as what we are]
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 · 67 lines · 28 tokens per session scan A 882d2abe1aeb
art-director is an agent published in the GitHub repository Dragoon0x/everything-design-taste (13 stars, last pushed 6mo ago), licensed MIT. It adds 28 tokens to every session and 614 once invoked, about $0.0001 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 agents, from other repositories
launch-film-analyst
Load when the user hands over a reference launch film or their own render (a local file, or a URL the user explicitly supplies and approves downloading) and wants it measured — cut rate, still share, first word, name timing, type cadence, typing speed, seams, endcard, loudness, onsets against motion — or reviewed…
design-md-consumer
Load when the user's project ships a design contract — a .design file (schema design.v1) or a DESIGN.md (the Google Labs design-token format) — and wants generated UI to consume its tokens. Discovers the contract, resolves precedence, normalizes the tokens, and produces TypeScript / CSS variables / a Tailwind config /…
agentation-fix-loop
Load when the user is running an Agentation two-session workflow and you are the Session 2 (fix) side. Watches MCP annotations from the critique session, reads each annotation's selector + file path + critique, applies the fix in code, commits, and loops to the next. Use only when the agentation MCP server is…
psychology-analyst
Evaluate design through behavioral psychology. Covers cognitive load, hierarchy, trust, persuasion, and dark patterns.
ui-ux-designer
Create interface designs, wireframes, and design systems. Masters user research, prototyping, and accessibility standards. Use proactively for design systems, user flows, or interface optimization.
perspective-audit
Deep accessibility review from 7 access perspectives. Activated by escalation from a11y-planner or a11y-critic when one or more perspectives are flagged at MEDIUM or HIGH alarm level.