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-seed)<a href="https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-seed"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-seed/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/commands/yojahny55/claude-wp-builder/wp-seed"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-seed.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.05280 |
| Opus 5 | $0.00015 | $0.02640 |
| Sonnet 5 | $0.00006 | $0.01056 |
| Haiku 4.5 | $0.00003 | $0.00528 |
Grade A, and why
wp-seed 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.
How it starts
The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WP Seed — Content Seeding from Demo HTML
Parse a demo HTML file (or multi-page demo directory), extract content via BEM class conventions, and seed it into WordPress using WP-CLI. Creates pages, imports media, populates ACF fields for all configured languages, and builds navigation menus.
Step 0: Read Project Manifest
Read .wp-create.json from the project root to obtain the WP-CLI wrapper and language configuration.
bash -c "cat .wp-create.json"
Extract and store:
$WP— the value ofwp_cli.wrapper(e.g.,docker exec my-project-wp wp --allow-root,wp --path=/var/www/html/my-project,ddev wp,lando wp,npx wp-env run cli wp)- Primary language —
languages.primary(e.g.,en) - Additional languages —
languages.additionalarray (e.g.,["es"]) - Project slug —
project.slug - Project path —
project.path
If .wp-create.json does not exist, fall back the same way /wp-debug does:
- Check if bare
wpis available:bash -c "which wp" - If available, set
$WPtowp(assume the current directory is the WordPress root) and take the languages from theLanguages:line of.claude/CLAUDE.mdinstead (first = primary, the rest = additional). - If
wpis not available either, abort with:"No
.wp-create.jsonfound and nowpon PATH. Run/wp-createto set up the WordPress environment, or install WP-CLI."
Verify WP-CLI connectivity before proceeding:
bash -c "$WP option get siteurl"
If this fails, abort with a message suggesting the user check that the WordPress environment is running.
Phase 1: Parse Demo HTML
Parse arguments
- First non-flag word = demo file path (optional). If provided and it points to a file, use that file.
--exclude-slugs <slug,slug,...>= optional comma-separated list of page slugs to skip when creating WP Pages in Phase 2 (default: none — existing behavior unchanged). Use this to avoid creating a WP Page for a slug that is served by a CPT archive (archive-<slug>.php/has_archive), which would otherwise collide.
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.
- 5d ago Changed · +5 lines d850a69ea814
- 9d ago First seen · 483 lines · 29 tokens per session scan A fcf9e7cd474d
wp-seed is a command published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 5,280 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.