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 isaacsight/kernel --skill kernel-chat-art-directiongit clone --depth 1 https://github.com/isaacsight/kernelWrote 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/isaacsight/kernel/kernel-chat-art-direction)<a href="https://agentmods.dev/skills/isaacsight/kernel/kernel-chat-art-direction"><img src="https://agentmods.dev/badge/skills/isaacsight/kernel/kernel-chat-art-direction/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/isaacsight/kernel/kernel-chat-art-direction"><img src="https://agentmods.dev/badge/skills/isaacsight/kernel/kernel-chat-art-direction.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 | $0.00065 | $0.00813 |
| Opus 5.5 | $0.00026 | $0.00325 |
| Sonnet 5.5 | $0.00013 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
kernel-chat-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 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kernel.chat Art Direction
Purpose
Turn an editorial argument into a recognizable visual world before writing page code. Make every choice carry meaning: material, type, scale, image treatment, negative space, rhythm, and motion.
Use $kernel-chat-web-design after this skill to implement the direction in the house system. Use $motion-design when the direction calls for substantial choreography. Use $kernel-chat-design-qa after implementation.
Start With the Editorial Sentence
Write one sentence in this form:
This issue argues that [claim], so the page should feel like [material place or process], moving from [opening state] to [closing state].
Do not select a visual style until this sentence is specific. Reject adjectives that do not imply a design decision, such as premium, modern, clean, or immersive.
Build the Direction
- Choose one material metaphor. Examples: an annotated field notebook, a night train timetable, a conservation ledger, a translucent laboratory sleeve. Define its paper, ink, edge, mark, and light behavior.
- Name the dominant gesture. Give the composition one memorable act: an interrupted column, a vertical specimen rail, a horizon that shifts between spreads, or a full-bleed plate cut by marginal evidence.
- Set the type hierarchy. Define display voice, reading voice, metadata voice, bilingual relationship, line length, and at least one intentional scale collision. Preserve kernel.chat's house type families unless the repository explicitly supports another licensed face.
- Design the cover as an argument. The cover must communicate issue identity at thumbnail size and reward close reading. Use one focal relationship, not a collage of every idea.
- Create one media grammar. Specify palette, crop logic, camera distance, texture, grain, illustration method, and what may repeat. Original assets may vary in composition while sharing the same material rules.
- Compose a rhythm, not a component stack. Alternate compression and release, image and text, evidence and reflection. Avoid repeated equal rectangles, uniform section padding, and one-card-per-idea layouts.
- Recompose for small screens. State what becomes the mobile anchor, what moves into the reading flow, what loses ornament, and what remains interactive. Mobile is a new composition, not a squeezed desktop.
- Write the motion intent. Name what moves, why it moves, its physical analogy, and its resting state. Do not prescribe decorative motion with no editorial role.
What ships with it
2 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.
- 1mo ago First seen · 57 lines · 65 tokens per session scan A 639aa2d2bda1
kernel-chat-art-direction is a skill published in the GitHub repository isaacsight/kernel (16 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 813 once invoked, about $0.0003 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 skills, from other repositories
persona-review
Seat a panel of real-distribution-grounded Korean citizen personas in front of a piece of UX, copy, or content and report how ordinary users would react. Samples 5 personas from a catalog, dispatches each as an independent panelist, and synthesizes their reactions. NOT a code/security/performance review (those are…
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
accessibility-audit
Reviews web and application accessibility against WCAG 2.2 AA and the European Accessibility Act (EAA, enforceable June 2025). Covers semantic HTML, ARIA usage, keyboard navigation, focus management, color contrast, screen-reader compatibility, form labels and errors, alternative text, motion and animation…
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
gpt-taste
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.