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 cosmicstack-labs/mercury-agent-skills --skill accessibilitygit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-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/cosmicstack-labs/mercury-agent-skills/accessibility)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/accessibility"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/accessibility.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 201 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 238 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 390 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00025 | $0.05019 |
| Opus 5 | $0.00013 | $0.02509 |
| Sonnet 5 | $0.00005 | $0.01004 |
| Haiku 4.5 | $0.00003 | $0.00502 |
Grade A, and why
accessibility 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 8d 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 — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Skill
Core Principles
1. Accessibility Is a Human Right
Digital accessibility is not a compliance checkbox — it's about ensuring everyone can use the web regardless of ability. Approximately 15% of the world's population experiences some form of disability. Building accessible products is the ethical choice, not just a legal requirement.
2. Start Early, Not as an Audit
Accessibility must be considered from the first wireframe, not discovered in a last-minute audit before launch. Retrofitting accessibility costs significantly more than building it in from the start. Include a11y in design critiques, sprint planning, and definition of done.
3. Nothing About Us Without Us
Design with, not for, people with disabilities. Test with real users who rely on assistive technologies. Automated tools catch only 30-40% of accessibility issues — human testing catches the rest. Include disabled people in your user research and usability testing.
4. Accessibility Improves UX for Everyone
Curb cuts benefit everyone, not just wheelchair users. Captions help people in noisy environments. High contrast helps on sunny days. Keyboard navigation helps power users. Accessibility features often become mainstream UX improvements.
5. Progress Over Perfection
Level AAA compliance is aspirational and not always achievable. Level AA is the practical target for most products. Don't let perfect be the enemy of good — ship AA-compliant work and document remaining issues for future iterations.
Accessibility Maturity Model
Level 1: Unaware
Accessibility is not considered at all. No guidelines, no testing, no training. Accessibility issues are found only when legal complaints arise. This is the starting point — and a liability.
Level 2: Reactive
Accessibility is addressed reactively — when a bug is filed, an audit is demanded, or a legal threat emerges. Fixes are firefighting exercises. No systemic improvements occur. Burnout is high among any team members advocating for a11y.
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.
- 8d ago First seen · 478 lines · 25 tokens per session scan A 948f0ca37577
accessibility is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (471 stars, last pushed 13d ago), licensed MIT. It adds 25 tokens to every session and 5,019 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
playground
Creates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually through controls, see a live preview, and copy out a prompt. Use when the user asks to make a playground, explorer, or interactive tool for a topic.
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.
fixing-accessibility
Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or reviewing WCAG compliance.
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.
generative-ui
Design system and guidelines for Claude's built-in generative UI — the showwidget tool that renders interactive HTML/SVG widgets inline in claude.ai conversations. This skill provides the complete Anthropic "Imagine" design system so Claude produces high-quality widgets without needing to call readme first. Use this…
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".