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/commands/yojahny55/claude-wp-builder/wp-audit)<a href="https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-audit"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-audit.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 | $0.00014 | $0.02977 |
| Opus 5 | $0.00007 | $0.01489 |
| Sonnet 5 | $0.00003 | $0.00595 |
| Haiku 4.5 | $0.00001 | $0.00298 |
Grade A, and why
wp-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 8d 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WP Audit — Comprehensive Site Audit
Run a comprehensive audit across security, SEO, accessibility, performance, and best practices. Reports issues with severity levels and offers to auto-fix what it can. Dispatches specialized audit agents and optionally configures Rank Math SEO and All-in-One WP Security.
Step 1: Parse Arguments
Parse $ARGUMENTS for:
- Category flags:
--security,--seo,--a11y,--performance,--best-practices --allflag (default if no category flags provided)--report-onlyflag (skip fix phase)--security-level basic|recommended|maximum(default:recommended, ignored if--report-only)
If --all or no category flags are present: enable all 5 categories (security, seo, a11y, performance, best-practices).
Step 2: Read Project Context
Read .claude/CLAUDE.md to extract:
- Function prefix (e.g.,
kairo_) - Theme slug
- Languages (primary + secondary)
- Theme directory path
- Industry (used for schema type: Organization vs LocalBusiness)
If .claude/CLAUDE.md does not exist, tell the user:
Error: Project not initialized. Run /wp-init first to set up the project context.
And stop execution.
Step 3: Detect Environment & Tier
Determine the audit tier:
Tier 1 (always): Code-only checks via Read, Grep, Glob.
Tier 2 (if .wp-create.json exists): Read .wp-create.json to get $WP wrapper. Set $WP to the value of wp_cli.wrapper. Enables WP-CLI runtime checks.
Tier 3 (if web-quality-skills installed): Check these paths in order:
~/.claude/skills/performance/SKILL.md.claude/skills/performance/SKILL.md- Glob for
**/web-quality-skills/skills/performance/SKILL.md
If any path exists, Tier 3 is available.
Print tier status:
=== Audit Tier Detection ===
Audit Tier: <Code | Code + Runtime | Code + Runtime + Lighthouse>
✓ Tier 1: Code analysis (always available)
<✓|✗> Tier 2: WP-CLI runtime checks (<.wp-create.json found|.wp-create.json not found>)
<✓|✗> Tier 3: External quality skills (<web-quality-skills detected|web-quality-skills not found>)
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.
- 8d ago First seen · 329 lines · 14 tokens per session scan A 54311c1ac447
wp-audit is a command published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 2,977 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 commands, from other repositories
audit
Run a full UI/UX design audit on the current project. Scores 12 dimensions and produces a markdown report with prioritized findings.
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
design-enforce
Use when code has drifted off the design system. Raw hex values and pixel numbers written where a token already exists, one-off components, library defaults left untouched. Finds every bypass and fixes it.
design-grill
Use when a design keeps getting reinvented every session. Interviews you until you share one understanding, then writes the vocabulary and the binding decisions into the repo so they survive the next context window.
design-triage
Use when a dwic audit report is full of findings and there is no plan. Ranks them into an order someone can work through, then works through it.
debug-helper
Use when something is broken and you need it diagnosed. A build failure, a runtime crash, a blank page, an unreadable error message, or behaviour that is simply wrong. Gives one exact fix, not a list of things to try.