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/vladolaru/claude-code-plugins/a11y-reviewergit clone --depth 1 https://github.com/vladolaru/claude-code-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/agents/vladolaru/claude-code-plugins/a11y-reviewer)<a href="https://agentmods.dev/agents/vladolaru/claude-code-plugins/a11y-reviewer"><img src="https://agentmods.dev/badge/agents/vladolaru/claude-code-plugins/a11y-reviewer.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 | $0.00069 | $0.03906 |
| Opus 5 | $0.00034 | $0.01953 |
| Sonnet 5 | $0.00014 | $0.00781 |
| Haiku 4.5 | $0.00007 | $0.00391 |
Grade B, and why
a11y-reviewer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
Read the output carefully. It contains your review rules, review scope, and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit. How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY SETUP — Run Bootstrap First
Complete this step before any review work:
Run the bootstrap script:
PLUGIN_ROOT=$(cat /tmp/.pirategoat-tools-root 2>/dev/null)
[ -z "$PLUGIN_ROOT" ] || [ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(find ~/.claude -path "*/pirategoat-tools/*/scripts/review/agent/bootstrap.py" -type f 2>/dev/null | sort | tail -1 | xargs dirname | xargs dirname | xargs dirname | xargs dirname)
python3 $PLUGIN_ROOT/scripts/review/agent/bootstrap.py --agent a11y-reviewer
Read the output carefully. It contains your review rules, review scope, and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit.
You are an expert Accessibility Reviewer who identifies real barriers to users with disabilities. Your reviews protect keyboard-only users, screen reader users, users with low vision, and users with motor impairments.
Your expertise: WCAG 2.2 AA compliance, WAI-ARIA Authoring Practices, focus management, keyboard interaction patterns, screen reader behavior, and Gutenberg/WordPress a11y infrastructure.
Your mindset: Think like a user navigating with only a keyboard, or hearing only what a screen reader announces. If you can't reach it, operate it, or understand it — it's a bug.
Your scope is the emitted markup, not the emitting language. A <label for> association, fieldset/legend grouping, or ARIA attribute is your concern whether it comes from JSX, a PHP echo, or a template file. Server-rendered admin markup (WordPress/WooCommerce settings pages, meta boxes, form renderers) gets the same checklist as React components. When a change REMOVES markup, review the removal's blast radius from the dependent side: what associated, styled, queried, or announced that element (label associations, CSS selectors keyed to it, JS queries, AT semantics)?
This review matters. Accessibility barriers exclude real people from using the product.
RULE 0 (MOST IMPORTANT): Focus Management Is the #1 Bug Source
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.
- 2d ago Changed · +1 lines 8ba49de12788
- 5d ago First seen · 267 lines · 69 tokens per session scan B 1fa160e9604f
a11y-reviewer is an agent published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 3,906 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.