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.
git clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/commands/perniemann/pncore/pn-audit-a11y)<a href="https://agentmods.dev/commands/perniemann/pncore/pn-audit-a11y"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn-audit-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/commands/perniemann/pncore/pn-audit-a11y"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn-audit-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 | $0.00043 | $0.00601 |
| Opus 5 | $0.00022 | $0.00300 |
| Sonnet 5 | $0.00009 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
pn-audit-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 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pn-audit-a11y
Start every response with: [pn-command] 🔺
Advanced (palette-hidden). Not in the
/slash palette. Invoked by the/pn-frontend-auditumbrella, or directly viaget_command("pn-audit-a11y").
Focused accessibility pass: audit WCAG contrast compliance, keyboard operability, ARIA usage, focus management, and semantic markup. No typography changes (use pn-audit-typography) — a11y only.
Flow
1. Context
Scope the audit: ask "Which pages or components?" if not provided. Check for any existing a11y notes in .pncore-stack.md.
2. Audit
Contrast (WCAG AA minimum):
- Body text ≥ 4.5:1 contrast vs background?
- Large text (≥18pt / 14pt bold) ≥ 3:1?
- UI components and focus indicators ≥ 3:1?
- Text-on-image: overlay or high-contrast background?
Keyboard navigation:
- All interactive elements reachable via Tab?
- Logical tab order (top-to-bottom, left-to-right)?
- No keyboard traps (modal close, dropdown dismiss)?
- Skip-to-content link present on pages with nav?
Focus management:
- Visible focus indicator on all interactive elements?
- Focus moves to modal content when modal opens?
- Focus returns to trigger when modal closes?
ARIA:
role,aria-label,aria-describedbyused where native semantics are insufficient?- No redundant ARIA (e.g.
role="button"on<button>)? - Dynamic content updates announced via
aria-live?
Semantic HTML:
- Headings in logical order (h1 → h2 → h3, no skips)?
- Landmark regions:
<main>,<nav>,<header>,<footer>? - Form inputs have associated
<label>elements? - Images have meaningful
alttext (emptyalt=""for decorative)?
Output: numbered issues table (location | issue | WCAG criterion | severity | suggested fix). Save to docs/audits/.
Gate: Present issues. Critical (contrast failures, keyboard traps) proceed immediately unless user says stop.
3. Fix
Apply in order: contrast failures → keyboard issues → ARIA fixes → semantic markup.
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 · 66 lines · 43 tokens per session scan A 581ffb2c8843
pn-audit-a11y is a command published in the GitHub repository perniemann/pnCore (0 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 601 once invoked, about $0.0002 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 commands, from other repositories
accessibility-audit
You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct comprehensive audits, identify barriers, provide remediation guidance, and ensure digital products are accessible to all users.
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
design-import
Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship…
component-search
Search 21st.dev component registry for production-ready React components. Finds components by natural language description, filters by framework and style system, returns ranked results with install instructions. Use when looking for UI components, finding alternatives to existing components, or sourcing design system…
ux-copy
Microcopy review and rewrite against the voice rubric. Produces a before/after table with severity per string and a clean rewrite block. Triggers on "review the copy", "fix the microcopy", "the error messages are bad", or "rewrite this". Use when reviewing or rewriting microcopy, fixing error messages that sound like…
ux-image-to-code
Take a design reference image (PNG/JPG/WebP), extract its dominant palette + canvas polarity + type signal via pure Pillow CV, match the result against the v2 palettes/styles manifests, and run the recommender on the synthetic brief. Returns the closest palette, the closest style, and a full recommended design system…