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 vosslab/vosslab-skills --skill color-accessibility-expertgit clone --depth 1 https://github.com/vosslab/vosslab-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/vosslab/vosslab-skills/color-accessibility-expert)<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/color-accessibility-expert"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/color-accessibility-expert/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/vosslab/vosslab-skills/color-accessibility-expert"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/color-accessibility-expert.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 | $0.00056 | $0.03192 |
| Opus 5 | $0.00028 | $0.01596 |
| Sonnet 5 | $0.00011 | $0.00638 |
| Haiku 4.5 | $0.00006 | $0.00319 |
Grade A, and why
color-accessibility-expert 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 10d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Color accessibility expert
Overview
Detect and fix WCAG color contrast across a repo. The primary outcome is a
set of source files whose colors all pass: locate color literals, measure
their contrast ratios, compute hue-preserving replacements for the failing
ones, and apply those replacements directly to the source files with
apply_color_fixes.py. Then re-audit to confirm every color passes,
optionally spot-check contrast in rendered images, and record the audited
result in docs/PALETTE_CONTRAST_AUDIT.md from evidence gathered during the
current run. The audit file documents the fix; the fixed source is the
deliverable.
Behavioral contract
This skill edits exactly two kinds of target-repo files, and both are first-class outcomes:
- Color values in source files -- the primary deliverable. During a fix
run (steps 3 and 4 below), replace each failing hex with the value
adjust_color.pyoraudit_palette.pycomputes, applied throughapply_color_fixes.py. This is the surface where the accessibility problem actually gets fixed. docs/PALETTE_CONTRAST_AUDIT.md-- the per-repo palette audit that documents the fixed result. Write or refresh that file only throughgenerate_palette_audit.py.
The generic WCAG method doc, docs/COLOR_CONTRAST_ACCESSIBILITY.md, is
propagated read-only from starter-repo-template and assumed present. Cite it
from the audit file, but never write it here.
Treat every other file in the target repo as read-only reference for this skill's own scripts, references, and generated output.
Ground every file path and color value in the generated audit table in files Read during the current run: the "Evidence rule" section below states the exact standard.
Project shape
Before step 1, frame the target: improve-existing (the repo has colors to audit and fix -- the common case) versus greenfield (the repo needs a palette created). Detection and both paths live in references/project_workflow.md. Classify one-off requests (single pair, one color, one image) with references/task_selection.md; route observed symptoms through references/topic_index.md.
What ships with it
20 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.
- agents/openai.yaml 363 B
- references/color_contrast_reference.md 2.9 KB
- references/palette_audit_template.md 2.5 KB
- references/project_workflow.md 2.6 KB
- references/task_selection.md 2.3 KB
- references/testing_and_oracles.md 2.5 KB
- references/topic_index.md 2.3 KB
- scripts/adjust_color.py 2.0 KB runs code
- scripts/apply_color_fixes.py 6.4 KB runs code
- scripts/audit_palette.py 5.8 KB runs code
- scripts/cam16_utils.py 3.6 KB runs code
- scripts/check_contrast.py 1.6 KB runs code
- scripts/color_utils.py 8.1 KB runs code
- scripts/extract_colors.py 4.8 KB runs code
- scripts/generate_color_wheel.py 12 KB runs code
- scripts/generate_palette_audit.py 8.7 KB runs code
- scripts/hue_layout.py 2.3 KB runs code
- scripts/image_contrast.py 6.1 KB runs code
- scripts/wheel_specs.py 5.9 KB runs code
- scripts/wheel_specs.yaml 612 B
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.
- 10d ago First seen · 227 lines · 56 tokens per session scan A 106fbfe8f4b8
color-accessibility-expert is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 15d ago), licensed MIT. It adds 56 tokens to every session and 3,192 once invoked, about $0.0003 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
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.