run-audit

run-audit is a command for coding agents from rohitg00/awesome-claude-code-toolkit. It costs 0 tokens per session (313 once invoked), scanned A, original, Apache-2.0.

An accessibility checker for websites and interface components, using WCAG, the international guidelines for making digital content usable by people with disabilities.

In plain words
What is it for?
Use it to check keyboard access, focus behavior, ARIA labels and roles, headings, color contrast, forms, image descriptions, captions, and other WCAG requirements.
Why use it?
It finds barriers that automated checks and visual review can miss, then groups them by likely impact. It also makes clear that manual testing is still needed because scans catch only some issues.

Command

Part of the a11y-audit plugin — 2 commands shipped together

About the project

Awesome Claude Code Toolkit is a curated collection of extensions and configuration for Claude Code, including agents, skills, commands, plugins, hooks, rules, templates, MCP configurations, and companion apps. It is for Claude Code users who want ready-made workflows and integrations for different development tasks. The catalogue add-ons are selected components from this toolkit.

rohitg00/awesome-claude-code-toolkit · 2,587 stars · on GitHub

Install

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.

agentmods
npx agentmods add commands/rohitg00/awesome-claude-code-toolkit/run-audit
Clone the repo
git clone --depth 1 https://github.com/rohitg00/awesome-claude-code-toolkit

Or install a11y-audit, the plugin that ships this one along with the rest of its 2 commands.

Wrote 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.

agentmods badge for run-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/rohitg00/awesome-claude-code-toolkit/run-audit.svg)](https://agentmods.dev/commands/rohitg00/awesome-claude-code-toolkit/run-audit)
Your own site
<a href="https://agentmods.dev/commands/rohitg00/awesome-claude-code-toolkit/run-audit"><img src="https://agentmods.dev/badge/commands/rohitg00/awesome-claude-code-toolkit/run-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 313 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00313
Opus 5 $0.00000 $0.00156
Sonnet 5 $0.00000 $0.00063
Haiku 4.5 $0.00000 $0.00031

Measured 5d ago against content hash 2a8b0add0b1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run-audit 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 5d 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.

plugins/a11y-audit/commands/run-audit.md · 29 lines

What it actually says

/run-audit - Run Accessibility Audit

Execute a comprehensive accessibility audit against WCAG guidelines.

Steps

  1. Ask the user for the target URL or component to audit
  2. Configure the audit scope: WCAG 2.1 Level A, AA, or AAA
  3. Run automated accessibility scanning using axe-core or similar engine
  4. Check all WCAG success criteria applicable to the content type
  5. Test keyboard navigation: all interactive elements reachable and operable
  6. Verify focus management: visible focus indicators, logical focus order
  7. Check ARIA usage: proper roles, states, properties, and landmark regions
  8. Validate heading hierarchy: logical order without skipping levels
  9. Test color contrast ratios: 4.5:1 for normal text, 3:1 for large text
  10. Check form accessibility: labels, error messages, required field indicators
  11. Verify media accessibility: alt text, captions, audio descriptions
  12. Compile findings into a prioritized report by impact level

Rules

  • Test against WCAG 2.1 AA as the minimum standard
  • Automated tools catch about 30% of issues; note that manual testing is also needed
  • Prioritize issues by user impact: critical (blocks access), serious, moderate, minor
  • Include WCAG success criterion reference for each finding
  • Test with actual assistive technology when possible (VoiceOver, NVDA)
  • Do not flag decorative images that correctly have empty alt attributes
  • Include remediation guidance with each finding
Changes

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.

  1. 5d ago First seen · 29 lines · 0 tokens per session scan A 2a8b0add0b1f

Subscribe to this mod's changes

run-audit is a command published in the GitHub repository rohitg00/awesome-claude-code-toolkit (2,587 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 313 tokens. 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.