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/armanzeroeight/fastagent-pluginsWrote 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/armanzeroeight/fastagent-plugins/audit-accessibility)<a href="https://agentmods.dev/commands/armanzeroeight/fastagent-plugins/audit-accessibility"><img src="https://agentmods.dev/badge/commands/armanzeroeight/fastagent-plugins/audit-accessibility/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/armanzeroeight/fastagent-plugins/audit-accessibility"><img src="https://agentmods.dev/badge/commands/armanzeroeight/fastagent-plugins/audit-accessibility.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 | $0.00010 | $0.00840 |
| Opus 5.5 | $0.00004 | $0.00336 |
| Sonnet 5.5 | $0.00002 | $0.00168 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade A, and why
audit-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 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Accessibility
Audit web page or component for accessibility issues and WCAG compliance.
Your Task
Perform accessibility audit and provide remediation recommendations.
Arguments
$1: File path or URL to audit
Steps
-
Read the code or page:
- Parse HTML/JSX structure
- Identify interactive elements
- Check for ARIA attributes
-
Check critical issues:
Missing alt text:
- Find all
<img>tags - Check for alt attribute
- Flag decorative images without alt=""
Form labels:
- Find all inputs
- Check for associated labels
- Verify aria-label or aria-labelledby
Keyboard navigation:
- Check for onClick on non-interactive elements
- Verify tabIndex usage
- Check for keyboard event handlers
Color contrast:
- Identify text and background colors
- Calculate contrast ratios
- Flag ratios below 4.5:1 (AA)
Heading hierarchy:
- Check heading levels (h1-h6)
- Verify no skipped levels
- Ensure single h1 per page
- Find all
-
Check ARIA usage:
- Verify valid ARIA attributes
- Check for redundant ARIA
- Validate ARIA roles
-
Provide severity ratings:
Critical (must fix):
- Missing alt text on images
- Form inputs without labels
- Keyboard traps
- Color contrast below 3:1
High (should fix):
- Color contrast below 4.5:1
- Missing ARIA labels on icon buttons
- Improper heading hierarchy
- Missing skip links
Medium (recommended):
- Missing lang attribute
- No focus indicators
- Redundant ARIA
- Missing landmarks
-
Provide remediation code:
For each issue, show before/after:
// Before <img src="logo.png" /> // After <img src="logo.png" alt="Company Logo" /> -
Generate accessibility report:
Accessibility Audit Report ========================== WCAG Level: AA Critical Issues (3): 1. Missing alt text on 5 images 2. Form input without label (email field) 3. Button not keyboard accessible High Priority (4): 1. Color contrast 3.2:1 on button (needs 4.5:1) 2. Heading hierarchy skips from h1 to h3 3. Icon button missing aria-label 4. No skip link for keyboard users Medium Priority (2): 1. Missing lang attribute on html 2. Focus indicator not visible Compliance Score: 65/100 Estimated fix time: 2-3 hours
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 · 149 lines · 10 tokens per session scan A 738531bf3f89
audit-accessibility is a command published in the GitHub repository armanzeroeight/fastagent-plugins (29 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 840 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
multi-frontend
Run a frontend-focused multi-model workflow for components, layouts, animation, and UI polish.
gan-design
Run a generator/evaluator design loop for frontend or visual work with bounded iterations and scoring.
flutter-build
Fix Dart analyzer errors and Flutter build failures incrementally. Invokes the dart-build-resolver agent for minimal, surgical fixes.
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.