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/siddik-web/wp-block-theme-converter/wp-theme-jsongit clone --depth 1 https://github.com/siddik-web/wp-block-theme-converterWrote 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/siddik-web/wp-block-theme-converter/wp-theme-json)<a href="https://agentmods.dev/commands/siddik-web/wp-block-theme-converter/wp-theme-json"><img src="https://agentmods.dev/badge/commands/siddik-web/wp-block-theme-converter/wp-theme-json.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 | $0.00025 | $0.01767 |
| Opus 5 | $0.00013 | $0.00883 |
| Sonnet 5 | $0.00005 | $0.00353 |
| Haiku 4.5 | $0.00003 | $0.00177 |
Grade A, and why
wp-theme-json 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wp-theme-json
Purpose: Generate a complete, valid theme.json (schema v3) from a design system, CSS custom properties, or design token specification.
Trigger
User types /wp-theme-json followed by:
- CSS custom properties (
:root { --color-primary: #000; ... }) - A design tokens spec (JSON, YAML, or plain description)
- A natural language description ("dark theme with gold accents and serif headings")
Workflow
Step 1: Extract Design Tokens
From the input, identify:
| Token Category | What to Extract |
|---|---|
| Colors | Primary, secondary, accent, background, surface, text, muted, border, success, warning, error |
| Gradients | Any linear/radial gradients used |
| Font Families | Heading, body, mono — note if self-hosted |
| Font Sizes | All discrete sizes — convert to fluid type if a clear scale exists |
| Spacing | Padding/margin scale (e.g., 4, 8, 16, 24, 32, 48, 64, 96) |
| Border Radius | sm, md, lg, pill, etc. |
| Shadows | sm, md, lg presets |
| Layout | Container width, wide width |
If anything is missing, use defaults from references/defaults.md.
Step 2: Build theme.json Structure
Read references/theme-json-schema.md for the full schema. The output MUST include:
{
"$schema": "https://schemas.wp.org/trunk/theme.json",
"version": 3,
"settings": {
"appearanceTools": true,
"useRootPaddingAwareAlignments": true,
"layout": {
"contentSize": "...",
"wideSize": "..."
},
"color": {
"palette": [...],
"gradients": [...],
"duotone": [...],
"defaultPalette": false,
"defaultGradients": false,
"customDuotone": true,
"link": true
},
"typography": {
"fluid": true,
"fontFamilies": [...],
"fontSizes": [...],
"lineHeight": true,
"letterSpacing": true,
"fontWeight": true,
"textTransform": true,
"textDecoration": true
},
"spacing": {
"spacingScale": { "operator": "*", "increment": 1.5, "steps": 7, "mediumStep": 1.5, "unit": "rem" },
"spacingSizes": [...],
"padding": true,
"margin": true,
"blockGap": true,
"units": ["px", "em", "rem", "vh", "vw", "%"]
},
"border": {
"color": true,
"radius": true,
"style": true,
"width": true
},
"shadow": {
"presets": [...],
"defaultPresets": false
},
"blocks": {
"core/button": { ... },
"core/heading": { ... }
}
},
"styles": {
"color": {
"background": "var(--wp--preset--color--background)",
"text": "var(--wp--preset--color--text)"
},
"typography": {
"fontFamily": "var(--wp--preset--font-family--body)",
"fontSize": "var(--wp--preset--font-size--medium)",
"lineHeight": "1.6"
},
"spacing": {
"padding": {
"top": "0",
"right": "var(--wp--preset--spacing--40)",
"bottom": "0",
"left": "var(--wp--preset--spacing--40)"
},
"blockGap": "var(--wp--preset--spacing--30)"
},
"elements": {
"h1": { ... },
"h2": { ... },
"h3": { ... },
"h4": { ... },
"h5": { ... },
"h6": { ... },
"link": {
"color": { "text": "var(--wp--preset--color--accent)" },
":hover": { "color": { "text": "var(--wp--preset--color--primary)" } },
":focus": { "color": { "text": "var(--wp--preset--color--primary)" } }
},
"button": {
"color": { ... },
":hover": { ... },
":focus": { ... },
":active": { ... }
}
},
"blocks": {
"core/button": { ... },
"core/heading": { ... },
"core/quote": { ... }
}
},
"templateParts": [
{ "name": "header", "title": "Header", "area": "header" },
{ "name": "footer", "title": "Footer", "area": "footer" }
],
"customTemplates": []
}
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 First seen · 210 lines · 25 tokens per session scan A 1d04995293ef
wp-theme-json is a command published in the GitHub repository siddik-web/wp-block-theme-converter (45 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 1,767 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 2026-08-30.
Other commands, from other repositories
wp-dev-learn
Extract learnings from the current session and update wp-dev-skills skill files — captures corrections, new rules, edge cases, and Common Mistakes entries discovered during real usage. Only globally applicable WP developer standards accepted — project-specific rules are redirected. Use suggest to see WP dev topics not…
wp-perf-review
WordPress performance code review - detects database anti-patterns, caching issues, hook problems, and scalability concerns.
wp-perf
Quick WordPress performance scan - fast triage using critical pattern detection.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
claude-recall
Update project context using the local LLM (Qwen2.5 0.5B).