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-cinematic-seed)<a href="https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-cinematic-seed"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-cinematic-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-cinematic-seed"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-cinematic-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 | $0.00056 | $0.00714 |
| Opus 5 | $0.00028 | $0.00357 |
| Sonnet 5 | $0.00011 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
wp-cinematic-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 10d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wp-cinematic-seed
Manifest shape
Must validate against cinematic-scroll-kit/schemas/scene.json. Top-level is an array of scene objects, plus an optional meta block:
{
"meta": {
"schema_version": "1.0.0",
"languages": ["en", "es"],
"scene_count": 9
},
"scenes": [
{
"scene_id": "scene-1",
"video_desktop": "https://kit.example/samples/scene-1.mp4",
"video_mobile": "https://kit.example/samples/scene-1.mobile.mp4",
"poster": "https://kit.example/samples/scene-1.jpg",
"eyebrow": "Field log — 01",
"eyebrow_es": "Bitácora — 01",
"headline": "Where the work begins.",
"headline_es": "Donde empieza el trabajo.",
"body": "<p>Long-form scene copy.</p>",
"cta_label": "Begin diagnostic",
"cta_url": "#diagnostic",
"align": "left",
"veil": "soft"
}
]
}
Pipeline
- Resolve manifest (CLI arg → theme demo → kit default).
- Validate against
schemas/scene.json— bail on parse/schema error with field path. - For each scene:
a. Look up existing row by
scene_id. b. If exists AND--forcenot set → skip (log "kept"). c. Sideload media: download URL →wp media import→ capture attachment ID. d. Build ACF row payload (same shape as/wp-cinematic-scene). e.update_row('cinematic_scenes', $i, $row, $home_id). - Flush caches.
- Print summary:
N added / N updated / N skipped.
Idempotence guarantees
- Sideload is deduplicated: if a media attachment with the same source URL exists in the Media Library, reuse its ID instead of re-downloading.
scene_idcollision means update, never duplicate-append.--dry-runproduces the same summary without writing — safe to run anytime to see diff vs current state.
Implementation note
The actual PHP script generated by wp-cinematic agent lives at <theme>/inc/seed-cinematic.php. This command is the orchestrator that calls wp eval-file <theme>/inc/seed-cinematic.php with the manifest path as an env var.
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.
- 10d ago First seen · 71 lines · 56 tokens per session scan A 66024e9e324b
wp-cinematic-seed is a command published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 714 once invoked, about $0.0003 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
yt
Route to the YouTube Agent Matrix orchestrator — the full pre-production pipeline.
tts:voices
Show the deterministic project → voice map (which repo sounds like which voice), current repo highlighted.
tts:voice
Choose the speech engine and voice for claude-tts, then restart the daemon to apply.
make-carousel
Design and produce a social media carousel (Instagram / LinkedIn / TikTok) — hook, narrative slides, CTA — with a consistent template and rendered slides.
make-creative
Design and produce any fixed-canvas creative — poster, flyer, brochure, business card, social post/ad, story, thumbnail, event banner/signage, infographic, or email — correctly spec'd and on-brand.
make-deck
Design and produce a presentation/deck (pitch, sales, conference, internal) using the Design Pro knowledge base — structure, slide design, and a producible output.