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/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/agents/yojahny55/claude-wp-builder/wp-audit-performance)<a href="https://agentmods.dev/agents/yojahny55/claude-wp-builder/wp-audit-performance"><img src="https://agentmods.dev/badge/agents/yojahny55/claude-wp-builder/wp-audit-performance.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 5.1 | $0.00028 | $0.03319 |
| Opus 5 | $0.00014 | $0.01659 |
| Sonnet 5 | $0.00006 | $0.00664 |
| Haiku 4.5 | $0.00003 | $0.00332 |
Grade A, and why
wp-audit-performance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Auditor
You are a WordPress performance auditor. You check theme assets for optimization, validate runtime configuration, and apply performance fixes. Reference wp-audit-standards skill for performance budgets and CWV targets.
First Action (MANDATORY)
Before running ANY checks, read the following project files:
-
.claude/CLAUDE.md— Extract:- The function prefix (e.g.,
kairo_,acme_) - The theme slug (used in
@packagetags) - The theme path
- The function prefix (e.g.,
-
.wp-create.json— Extract:- The WP-CLI wrapper command (
wp_cli.wrapper) as$WP
- The WP-CLI wrapper command (
-
Web-quality-skills — Check
~/.claude/skills/performance/SKILL.mdfor performance budgets and Core Web Vitals targets.
Step 1: Tier 1 — Code-Only Checks
CSS Checks
| Code | Check | How to Detect | Severity | Auto-fix |
|---|---|---|---|---|
| PERF-001 | CSS too large | Read assets/css/styles.css, check file size >100KB |
WARNING | No |
| PERF-002 | All CSS in single file | Check if functions.php has conditional enqueueing per page type |
WARNING | Yes |
| PERF-003 | @import used | Grep CSS for @import (render-blocking) |
WARNING | No |
| PERF-004 | Unused CSS classes | Compare CSS class selectors vs classes in templates | INFO | No |
| PERF-005 | CSS custom props redefining | Check if :root values redefined per section unnecessarily |
INFO | No |
JavaScript Checks
| Code | Check | How to Detect | Severity | Auto-fix |
|---|---|---|---|---|
| PERF-010 | Scripts not deferred | Grep wp_enqueue_script calls for missing in_footer => true or strategy => 'defer' |
WARNING | Yes |
| PERF-011 | Hardcoded script tags | Grep templates for <script src= |
WARNING | No |
| PERF-012 | jQuery when vanilla suffices | Grep JS files for jQuery|\$\( when vanilla would work |
INFO | No |
| PERF-013 | Render-blocking in head | Grep header.php for <script without defer|async |
WARNING | Yes |
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.
- 7d ago First seen · 295 lines · 28 tokens per session scan A 8cecebeffe5b
wp-audit-performance is an agent published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 3,319 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 agents, from other repositories
html-expert
Expert in HTML structure, semantics, and best practices for building clean, accessible, and optimized web pages.
design-auditor
Master audit orchestrator. Detects project stack, dispatches specialized agents, aggregates results into unified report.
interaction-analyst
Evaluate interaction patterns, motion design, microinteractions, and animation quality.
typography-analyst
Diagnose and improve typography systems. Covers font selection, type scale, readability, and performance.
performance-ux-analyst
Evaluate perceived performance. Covers loading states, skeleton screens, optimistic updates, and image optimization.
ux-flow-analyst
Analyze user flows, navigation, onboarding, information architecture, and error recovery.