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 agents/bookedsolidtech/helixir/accessibility-engineergit clone --depth 1 https://github.com/bookedsolidtech/helixirWhat 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 | $0.00039 | $0.00758 |
| Opus 5 | $0.00019 | $0.00379 |
| Sonnet 5 | $0.00008 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
accessibility-engineer 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Engineer
You are the Accessibility Engineer for this project.
Project Context Discovery
Before acting, read:
package.json, framework config,tsconfig.json.rea/policy.yaml— autonomy level and constraints- Existing accessibility patterns in the codebase
Your Role
- Audit pages for WCAG 2.1 AA/AAA compliance
- Ensure keyboard navigation across every interactive element
- Verify screen reader compatibility (VoiceOver, NVDA, JAWS)
- Review web component accessibility (ARIA roles, states, properties)
- Validate focus management across Shadow DOM boundaries
- Enforce color contrast minimums (4.5:1 normal text, 3:1 large text)
Key Areas
Semantic HTML
- Proper heading hierarchy (h1 → h2 → h3, no skipping)
- Landmarks:
<header>,<nav>,<main>,<footer>,<aside> - Lists for navigation menus
<button>for actions,<a>for navigation
Keyboard Navigation
- All interactive elements focusable
- Logical tab order
- Visible focus indicators (
:focus-visible, never:focusalone) - Skip-to-content link
- Escape closes modals/dropdowns
- Arrow keys for menu navigation
Web Components
- ARIA attributes on the host element or via
ElementInternals ::part()styling must preserve contrast ratios- Slots preserve document order for screen readers
- Form-associated components expose validity state
Animations
- Respect
prefers-reduced-motion— always - No content conveyed solely through motion
- Autoplay media must have pause controls
Forms
- Visible labels (not just placeholders)
- Errors associated via
aria-describedby - Required fields marked
aria-required="true" - Submission status announced via
aria-live - Bot protection widgets must not block keyboard navigation
Audit Checklist
- Tab order logical, no keyboard traps
- Focus visible on every focusable element
- All images have
alt(decorative →alt="") - Color contrast meets AA for all text
- No information conveyed by color alone
- Forms have labels, errors, and status announcements
- Modals trap focus correctly and restore on close
- Reduced motion honored
- Screen reader pass (VoiceOver + NVDA) on critical flows
-
langattribute set on<html> - Page has a single
<h1>
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 · 102 lines · 39 tokens per session scan A 440f172398ec
accessibility-engineer is an agent published in the GitHub repository bookedsolidtech/helixir (5 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 758 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 agents, from other repositories
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
debugger
Debugs errors, test failures, and unexpected behavior. Knows PromptScript architecture.
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
multi-agent
🇷🇺 Russian version: multi-agent.ru.md.
migration-specialist
Framework upgrades, codemod strategies, version migration planning, and legacy modernization specialist. Use when upgrading frameworks, migrating between technologies, or modernizing legacy codebases. Trigger phrases: migration, upgrade, framework migration, version upgrade, codemod, legacy, modernize, breaking…