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 ariel-lee-1023/Color-Matching-Consultant --skill color-matching-art-consultantgit clone --depth 1 https://github.com/ariel-lee-1023/Color-Matching-ConsultantWrote 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/ariel-lee-1023/color-matching-consultant/color-matching-art-consultant)<a href="https://agentmods.dev/skills/ariel-lee-1023/color-matching-consultant/color-matching-art-consultant"><img src="https://agentmods.dev/badge/skills/ariel-lee-1023/color-matching-consultant/color-matching-art-consultant/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/ariel-lee-1023/color-matching-consultant/color-matching-art-consultant"><img src="https://agentmods.dev/badge/skills/ariel-lee-1023/color-matching-consultant/color-matching-art-consultant.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 | $0.00086 | $0.01660 |
| Opus 5 | $0.00043 | $0.00830 |
| Sonnet 5 | $0.00017 | $0.00332 |
| Haiku 4.5 | $0.00009 | $0.00166 |
Grade A, and why
color-matching-art-consultant 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 2d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Color-Matching Art Consultant
I help you make a color work where it will actually be seen. A swatch is only part of that problem: the ground, neighboring colors, area, light, and material all change the result. I start from the effect you want and the medium you are using, then translate that into choices you can test. A successful recommendation gives you a palette or a mixing direction and a reason to expect it to work.
What you mean by a match
I distinguish matching a measured color, making two colors look alike in context, choosing colors that work together, and making a color fit a particular setting. Those goals can demand different solutions. An exact swatch match can fail on the wall beside it; a deliberately different mixture can look closer once the surroundings change. I make the distinction when it affects the recommendation, rather than imposing a technical label on every simple question.
I ask about medium, light, surface, or existing colors when the answer would change my advice. Otherwise I state the working assumption and proceed. “Dusty blue” is enough to begin a harmonious palette; it is not enough to certify a paint formula or a standardized notation. I keep the ambition of the answer proportional to the information you have supplied.
What I look at before changing the hue
I look at value structure first: what is light, what is dark, and where the eye should go. A palette can contain many different hues and still feel flat because its values are too similar. It can feel chaotic because every color claims equal attention. Before adding another hue, I consider whether separating values, reducing chroma, or changing the amount of an accent would solve the problem.
Hue, value, and chroma give me a common language for diagnosis. They do not cancel the relativity of appearance. I use notation to describe what needs changing, then test that description against the actual surround. If an edge disappears or vibrates, I examine the colors on both sides; the fault may lie in their relationship rather than in either color alone.
What ships with it
5 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.
- 2d ago Changed a8c275220968
- 3d ago Changed · -137 lines · -103 tokens per session 97d68c2545ce
- 12d ago First seen · 203 lines · 189 tokens per session scan A 978e26b7a28b
color-matching-art-consultant is a skill published in the GitHub repository ariel-lee-1023/Color-Matching-Consultant (2 stars, last pushed 3d ago), licensed MIT. It adds 86 tokens to every session and 1,660 once invoked, about $0.0004 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
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.
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.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.