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 agentmods add commands/kumaran-is/claude-code-onboarding/fixing-accessibilitygit clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/kumaran-is/claude-code-onboarding/fixing-accessibility)<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/fixing-accessibility"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/fixing-accessibility.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 | $0.00037 | $0.00924 |
| Opus 5 | $0.00018 | $0.00462 |
| Sonnet 5 | $0.00007 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
fixing-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 yesterday.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fixing-accessibility
Audit for accessibility violations and produce targeted, minimal fixes.
Usage
/fixing-accessibility— apply accessibility constraints to all UI work in this session/fixing-accessibility <file>— audit the specified file and report violations with fixes
Process
1. Load Skill
Load the accessibility-audit skill to get platform-specific patterns and checklists.
2. Detect Stack
- If argument is a
*.dartfile → Flutter audit (useflutter-mobile/reference/accessibility-audit-checklist.md) - If argument is a
*.html,*.ts, or*.scssfile → Angular audit (useangular-spa/reference/accessibility-checklist.md) - If no argument → session mode: apply constraints from both checklists to all subsequent UI work
3. File Audit Mode (/fixing-accessibility <file>)
Dispatch accessibility-auditor agent against the specified file.
For each violation found, report:
## Accessibility Audit: <file>
### Violations
| Priority | Rule | Line | Snippet | Fix |
|----------|------|------|---------|-----|
| CRITICAL | Accessible name missing | :42 | `<button><svg>...</svg></button>` | Add `aria-label="Close"` to button, `aria-hidden="true"` to SVG |
| HIGH | aria-invalid not set | :87 | `<input id="email" />` | Add `aria-invalid="true"` and `aria-describedby="email-err"` |
### Summary
- Critical: N
- High: N
- Medium: N
- Low: N
- Status: PASS (0 violations) / FAIL (N violations)
4. Session Mode (/fixing-accessibility)
Apply these constraints to all UI work in this conversation:
Angular — enforce before writing any interactive element:
- Every
<button>,<a>,<input>,<select>,<textarea>must have an accessible name - Icon-only buttons:
aria-labelrequired, SVG getsaria-hidden="true" - Form errors:
aria-describedby+aria-invalid="true"on the field - Modals: trap focus, restore on close,
Escapedismisses - Dynamic content:
aria-livefor errors and status updates - No
tabindex > 0 - Touch targets: minimum 44x44px
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.
- yesterday First seen · 96 lines · 37 tokens per session scan A 4f3dfd476c8c
fixing-accessibility is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 924 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 2026-09-03.
Other commands, from other repositories
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
wcag-audit
Accessibility audit based on WCAG 2.1/2.2 and the axe-core reference.
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.
build-verify
Run the full build / test / analyze / format verification pass for this Flutter app.
create-pr-from-staged-changes
You are helping to create a pull request following the iOS team's standard template.
mobile-performance-check
Analyze mobile app for performance issues using the mobile-best-practices database.