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 hcaiano/skills --skill art-directorgit clone --depth 1 https://github.com/hcaiano/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/hcaiano/skills/art-director)<a href="https://agentmods.dev/skills/hcaiano/skills/art-director"><img src="https://agentmods.dev/badge/skills/hcaiano/skills/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/skills/hcaiano/skills/art-director"><img src="https://agentmods.dev/badge/skills/hcaiano/skills/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 | $0.00043 | $0.00712 |
| Opus 5 | $0.00022 | $0.00356 |
| Sonnet 5 | $0.00009 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
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 12d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Art Director
Explore visual directions, curate them with the user, and converge on one defensible choice. Do not implement the product while this skill is active.
Compose, do not copy
- Read and use
imagegenfor every generated concept. Its generation, editing, validation, and save-path rules own the image work. - For a brand or identity exploration, read
brandkitonly after a direction has earned a system proof. Do not generate a brand board for every early idea. - Run intake as a grilling conversation: investigate facts yourself, ask decisions one at a time, include your recommended answer, and wait for the user's reply. No separate intake skill is required.
- If the current runtime cannot generate images, use
pairto give a Codex peer the generation brief. When image generation is available directly, Herdr is unnecessary. - Obey the current project's agent, product, brand, and design-system instructions.
Workflow
- Inspect. Determine whether this is blank-slate or constrained by an existing brand. Read available references, product context, design tokens, and existing surfaces before asking questions.
- Intake. Resolve the audience, surface, communication goal, required content, format, references, anti-references, hard brand constraints, and decision deadline. Ask only what materially changes the exploration.
- Frame directions. Name three to five concrete visual premises. Each direction needs a different underlying rule for composition, hierarchy, imagery, and mood. "More options" is not a direction.
- Generate breadth. Use one
imagegencall per direction. Keep the functional content and format constant so the visual ideas are comparable. Preserve an established identity; for blank-slate work, explore a genuine range. Keep the exact prompt for every output. - Curate. Inspect every image. Identify it by filename or stable ID and explain what works, what fails, and which reusable trait it contributes. Maintain a shortlist and a rejected-pattern list. Ask the user for the next decision one question at a time.
- Refine. Generate two or three variants of the strongest direction. Change one named trait at a time instead of remixing everything.
- Prove the system. Stress-test the winner on an adjacent page, state, or
asset. For identity work, use
brandkitto create one coherent system board from the selected direction. - Hand off. Return the selected asset paths, exact prompts, visual rules,
rejected patterns, and remaining trade-offs. Save project-bound outputs in
the workspace according to
imagegen; preview-only outputs may remain inline.
What ships with it
1 file 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.
- 12d ago First seen · 62 lines · 43 tokens per session scan A 371cc757a830
art-director is a skill published in the GitHub repository hcaiano/skills (3 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 712 once invoked, about $0.0002 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-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
visual-plan
Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.
visual-edit
Open a running local app in Design overview mode as URL-backed iframe screens for visual editing, flow review, duplication, and route-state exploration. Use when the user asks to inspect, compare, or edit a real local app visually in Design.
muapi-ui-design
Generate high-fidelity UI/UX mockups for mobile and web apps using Atomic Design principles — creates wireframes and design systems via muapi.ai.
display-glasses-with-jetpack-compose-glimmer
Provides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI toolkit. This skill covers foundational Glimmer design principles, workflows for implementing Jetpack Compose Glimmer, and interaction models for the glasses form factor. Use this skill to build an…
baseline-ui
Quickly deslop UI code by fixing spacing, hierarchy, typography, and small layout issues. Use when the interface needs a fast cleanup or polish pass.