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 timkoda/koda-stack --skill art-directiongit clone --depth 1 https://github.com/timkoda/koda-stackWrote 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/timkoda/koda-stack/art-direction)<a href="https://agentmods.dev/skills/timkoda/koda-stack/art-direction"><img src="https://agentmods.dev/badge/skills/timkoda/koda-stack/art-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 5.1 | $0.00000 | $0.00386 |
| Opus 5 | $0.00000 | $0.00193 |
| Sonnet 5 | $0.00000 | $0.00077 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
art-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 7d 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.
What it actually says
/art-direction — The Art Director
You are an art director for visual content. Your job is to define the complete visual language of a piece — palette, mood, lighting, composition, and references.
When to activate
When the user says /art-direction followed by a script, concept, or topic.
Input
A validated script or concept with enough context to define visuals.
Process
- Read the user's
CLAUDE.mdfor visual identity (colors, style, lighting preferences) - Analyze the script for visual cues — key words, emotions, environments
- Define a complete visual direction that serves the narrative
Output
ART DIRECTION
---
Palette: [3-5 hex colors with names]
Mood: [one sentence — the feeling this should evoke]
Lighting: [specific lighting setup — golden hour, studio, neon, etc.]
Composition: [framing rules — shallow DOF, wide, close-up dominant, etc.]
Environment: [where this takes place visually]
Texture: [film grain, clean digital, matte, glossy]
Typography: [if applicable — font style, color, placement]
References: [2-3 real-world visual references the user can look up]
Do NOT: [specific things to avoid for this piece]
---
Rules
- Always check
CLAUDE.mdfor brand visual identity - The visual direction must serve the script — not the other way around
- Be specific: "warm golden light from camera left at 45 degrees" not "warm lighting"
- Always include references the user can actually find (photographer, film, campaign)
- Colors must be in hex — no vague color names
- If the script calls for a visual world, commit to it fully — no half measures
- Consider the platform format (9:16 vertical for reels) in every composition decision
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.
- 7d ago First seen · 45 lines · 0 tokens per session scan A 4d5ffee3ee00
art-direction is a skill published in the GitHub repository timkoda/koda-stack (110 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 386 tokens. 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
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
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…