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 dallay/agents-skills --skill markdown-a11ygit clone --depth 1 https://github.com/dallay/agents-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/dallay/agents-skills/markdown-a11y)<a href="https://agentmods.dev/skills/dallay/agents-skills/markdown-a11y"><img src="https://agentmods.dev/badge/skills/dallay/agents-skills/markdown-a11y.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 | $0.00054 | $0.01969 |
| Opus 5 | $0.00027 | $0.00984 |
| Sonnet 5 | $0.00011 | $0.00394 |
| Haiku 4.5 | $0.00005 | $0.00197 |
Grade A, and why
markdown-a11y 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
- Reviewing markdown files (READMEs, docs, blog posts, GitHub profiles) for accessibility
- Creating new documentation and wanting to ensure inclusivity from the start
- Auditing existing markdown content for screen reader compatibility
- When asked to improve documentation quality with accessibility in mind
Critical Patterns
- Descriptive Links: Never use "click here", "here", "this", "read more" as link text. Link text must make sense when read out of context.
- Image Alt Text: Every image needs meaningful alt text. Empty alt
![]()is only acceptable for explicitly decorative images. Filenames and generic words like "screenshot" are not valid alt text. - Heading Hierarchy: One H1 per document, never skip levels (e.g.,
##to####is a violation), and never use bold text as a fake heading. - Proper Lists: Always use markdown list syntax (
-,*,+,1.). Never use emoji or special characters as bullet points. - Emoji Restraint: Don't stack multiple consecutive emoji. Don't use emoji as the sole conveyor of meaning.
Review Priority
When multiple issues exist, fix in this order:
- Missing or empty alt text on images
- Skipped heading levels or heading hierarchy issues
- Non-descriptive link text
- Emoji used as bullet points or list markers
- Plain language improvements
Code Examples
1. Descriptive Links
<!-- BAD: generic link text -->
Read my blog post [here](https://example.com).
For more info, [click here](https://example.com/docs).
Check out [this](https://example.com/guide) guide.
<!-- GOOD: descriptive, self-contained link text -->
Read my blog post "[Crafting an accessible resume](https://example.com)".
For more info, see the [API authentication guide](https://example.com/docs).
Check out the [getting started guide](https://example.com/guide).
<!-- BAD: bare URL in prose -->
See https://example.com/docs for details.
<!-- GOOD: wrapped in descriptive link -->
See the [project documentation](https://example.com/docs) for details.
<!-- BAD: identical text, different destinations -->
See [documentation](https://example.com/api) for the API.
See [documentation](https://example.com/cli) for the CLI.
<!-- GOOD: unique, distinguishable text -->
See the [API documentation](https://example.com/api).
See the [CLI documentation](https://example.com/cli).
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 · 260 lines · 54 tokens per session scan A 7623480ef1e9
markdown-a11y is a skill published in the GitHub repository dallay/agents-skills (2 stars, last pushed 16d ago), licensed MIT. It adds 54 tokens to every session and 1,969 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…