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 skills add yojahny55/claude-wp-builder --skill wp-audit-standardsgit clone --depth 1 https://github.com/yojahny55/claude-wp-builderWrote 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/skills/yojahny55/claude-wp-builder/wp-audit-standards)<a href="https://agentmods.dev/skills/yojahny55/claude-wp-builder/wp-audit-standards"><img src="https://agentmods.dev/badge/skills/yojahny55/claude-wp-builder/wp-audit-standards/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/skills/yojahny55/claude-wp-builder/wp-audit-standards"><img src="https://agentmods.dev/badge/skills/yojahny55/claude-wp-builder/wp-audit-standards.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.02669 |
| Opus 5 | $0.00013 | $0.01334 |
| Sonnet 5 | $0.00005 | $0.00534 |
| Haiku 4.5 | $0.00003 | $0.00267 |
Grade A, and why
wp-audit-standards 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 12d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WP Audit Standards
This skill defines the audit criteria, severity levels, report format, and quality thresholds used by all wp-audit agents.
Severity Levels
| Severity | Meaning | Action |
|---|---|---|
| CRITICAL | Security vulnerability, complete accessibility failure, broken core functionality | Fix immediately |
| WARNING | Best-practice violation, degraded UX, performance issue | Fix before delivery |
| INFO | Optimization opportunity, minor improvement | Fix when convenient |
Report JSON Schema
All audit agents MUST output findings in this format:
{
"category": "security|seo|a11y|performance|best-practices",
"tier": 1,
"issues": [
{
"severity": "critical|warning|info",
"code": "SEC-001",
"message": "Human-readable description",
"file": "path/to/file.php",
"line": 42,
"auto_fixable": true,
"fix_method": "Description of how to fix"
}
],
"summary": {
"total": 0,
"critical": 0,
"warning": 0,
"info": 0,
"auto_fixable": 0
}
}
Field Requirements
category— one of:security,seo,a11y,performance,best-practicestier— integer 1–3 indicating which audit tier produced the findingissues— array of issue objects (may be empty)severity— one of:critical,warning,infocode— prefixed issue code (see Issue Code Prefixes below)message— human-readable description of the problemfile— relative path to the affected fileline— line number (0 if not applicable)auto_fixable— boolean indicating whether the agent can safely fix thisfix_method— description of the fix approachsummary— counts aggregated from the issues array
Issue Code Prefixes
| Prefix | Domain |
|---|---|
SEC-xxx |
Security |
SEO-xxx |
SEO |
A11Y-xxx |
Accessibility |
PERF-xxx |
Performance |
WP-xxx |
Best Practices |
Audit Tiers
Tier 1 — Code-only (always available)
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.
- 12d ago First seen · 240 lines · 25 tokens per session scan A 4168b35e923b
wp-audit-standards is a skill published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 2,669 once invoked, about $0.0001 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 skills, from other repositories
a11y-audit
Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…
river-review-frontend
A frontend review skill that checks user-interface changes for accessibility, design-system consistency, styling issues, UI states, and framework boundaries in React and Next.js.
Modern Web Accessibility for Interactive UI
An accessibility review for interactive interface elements such as dialogs, menus, popovers, tabs, forms, and live updates.
Modern Web Semantic + Platform-Native
A review rule for web interfaces that checks whether standard HTML elements, browser features, and modern CSS can replace custom JavaScript or generic clickable elements.
a11y Accessible Name Basics
A Japanese-language accessibility check for accessible names on images, buttons, links, and form fields. An accessible name is the label a screen reader uses to identify an interface element.
route-codex-review
Forced adversarial review pre-delivery — hands Claude-generated code, content, or plans to Codex (GPT-5.5) to find bugs, security risks, missing tests, and missed edge cases. Trigger when the user says "review the code you wrote", "check your work", "second opinion", "sanity-check what you wrote", "adversarial…