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 commands/yojahny55/claude-wp-builder/wp-initgit 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-init)<a href="https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-init"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-init.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 | $0.00024 | $0.06768 |
| Opus 5 | $0.00012 | $0.03384 |
| Sonnet 5 | $0.00005 | $0.01354 |
| Haiku 4.5 | $0.00002 | $0.00677 |
Grade A, and why
wp-init 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 today.
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 — 614 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WP Init — Project Scaffolding
Scaffold a new WordPress project from the starter theme, configure i18n, and generate the project CLAUDE.md.
Step 0.5: Select Starter Template
Ask the user to choose a starter template:
Select a starter template:
- Tailwind Starter — Tailwind CSS 4 + WordPress Scripts build pipeline, BrowserSync
- Cinematic Starter — Scroll-driven cinematic reel (persistent video stage, scene scrub on desktop, autoplay-loop on mobile). Requires the cinematic-scroll-kit skill.
Store the selection as $TEMPLATE:
- Option 1 →
tailwind - Option 2 →
cinematic
Default: tailwind (if user presses Enter without selecting).
There is no "Basic Starter" any more. starter-theme/__starter__/ was removed
in 3600552 as superseded by the Tailwind template, but this command kept
offering it as option 1 AND as the Enter-key default — so the most likely path
through /wp-init copied a directory that does not exist. Treat basic as an
alias for tailwind if a caller still passes --template=basic, rather than
failing on it.
If $TEMPLATE = cinematic
This branch follows a different scaffolding shape — the page is one continuous reel, not discrete sections. After Step 0.6, dispatch to /wp-cinematic-init for the cinematic-specific flow:
- Resolve
cinematic-scroll-kit(globally-installed skill →./.cinematic-kit/→ vendored fallback instarter-theme/__cinematic__/assets/cinematic-kit/). - If none present, offer:
npx skills add yojahny55/cinematic-scroll-kit -g -y(recommended). Decline → use vendored fallback. - Copy
starter-theme/__cinematic__/as the theme. - Run the
wp-cinematicagent againstschemas/scene.jsonto generatefields/scenes.php,fields/trailing-sections.php(if hybrid),inc/seed-cinematic.php, and per-scene template fragments. - Skip the per-section
/wp-sectionloop. Author scenes via/wp-cinematic-scene <n>and append trailing flex sections via/wp-section <name> --hybridif hybrid mode is on. - Seed with
/wp-cinematic-seed(uses kit sample videos).
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.
- today Changed · +18 lines 81c47c87be5b
- 2d ago Changed · +34 lines 237c01360dbe
- 5d ago First seen · 562 lines · 24 tokens per session scan A 50418c7a3c07
wp-init is a command published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 6,768 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
setup
SoDam-Design-Kit 설정 마법사 — config.json 생성 + shadcn 컴포넌트 스캔으로 component-map 초기 시드.
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.
audit
Run a full UI/UX design audit on the current project. Scores 12 dimensions and produces a markdown report with prioritized findings.