Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/harshii0509/designStacknpx agentmods add skills/harshii0509/designstack/a11yWrote 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/harshii0509/designstack/a11y)<a href="https://agentmods.dev/skills/harshii0509/designstack/a11y"><img src="https://agentmods.dev/badge/skills/harshii0509/designstack/a11y/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/harshii0509/designstack/a11y"><img src="https://agentmods.dev/badge/skills/harshii0509/designstack/a11y.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 | $0.00062 | $0.02500 |
| Opus 5.5 | $0.00025 | $0.01000 |
| Sonnet 5.5 | $0.00012 | $0.00500 |
| Haiku 4.5 | $0.00006 | $0.00250 |
Grade A, and why
ds-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 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble
"../lib/env.sh" "a11y"
What accessibility means (explain this to the user if they haven't run /ds-a11y before)
"Accessibility means your website works for everyone — including people who are blind and use a screen reader to hear the page, people with low vision who need high contrast text, people who are color-blind, and people who use a keyboard instead of a mouse. Many countries also have legal requirements around this.
I'll check your site against the main rules and give you a grade from A to D, plus a screenshot showing exactly where each problem is."
This is a one-page accessibility audit. If the user wants a broader launch review, route them to /ds-polish instead.
Step 1 — Load Design Bible (if present)
If DESIGN_BIBLE is yes, follow the standard extraction protocol in lib/bible-reader.md. Focus on L1 Colors and L4 component rules for contrast checking.
Step 2 — Get the URL
Ask the user:
"What page should I check for accessibility? Give me the URL (e.g.
http://localhost:3000or your live URL). The home page is a good start, or try your most important page like checkout or signup."
Step 2 — Take a baseline screenshot
If BROWSE is not NOT_FOUND:
$B goto <URL>
$B screenshot /tmp/dstack-a11y-before.png
If the URL is not reachable:
"Your project doesn't seem to be running right now. Start it with
npm run dev(ornpm start) and then give me the URL — usually http://localhost:3000. I'll wait."
Do not continue until the user confirms the project is running.
Show the screenshot to the user:
"Here's your page. Let me run the accessibility check now."
Step 3 — Take screenshot and run accessibility audit
If BROWSE is not NOT_FOUND:
"../lib/visual-audit.sh" screenshot "<URL>" "a11y" "before"
If the URL is not reachable, run and show the output of:
"../lib/visual-audit.sh" not_running
Do not continue until the user confirms the project is running.
What ships with it
1 file 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 · 288 lines · 62 tokens per session scan A fd6f5cb2dc42
ds-a11y is a skill published in the GitHub repository harshii0509/designStack (13 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 2,500 once invoked, about $0.0002 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.