Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Lombiq/Orchard-Core-Agent-Skillsnpx agentmods add skills/lombiq/orchard-core-agent-skills/orchard-core-themingWrote 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/skills/lombiq/orchard-core-agent-skills/orchard-core-theming)<a href="https://agentmods.dev/skills/lombiq/orchard-core-agent-skills/orchard-core-theming"><img src="https://agentmods.dev/badge/skills/lombiq/orchard-core-agent-skills/orchard-core-theming/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/skills/lombiq/orchard-core-agent-skills/orchard-core-theming"><img src="https://agentmods.dev/badge/skills/lombiq/orchard-core-agent-skills/orchard-core-theming.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 | $0.00067 | $0.01082 |
| Opus 5 | $0.00034 | $0.00541 |
| Sonnet 5 | $0.00013 | $0.00216 |
| Haiku 4.5 | $0.00007 | $0.00108 |
Grade A, and why
orchard-core-theming 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 12d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchard Core Theming
Use this skill for Orchard Core theming and content-definition/recipe work.
How to use
- Path A (task match): scan the Tasks list; if the request matches, open
references/TASK-MAP.mdand go directly to the leaf files. - Path B (exploration): use the section cues to pick a reference section, open that section's
INDEX.md, then choose the leaf file it points to. - Determine Razor vs Liquid early using the workflow in
references/TASK-MAP.md. If it cannot be decided, fall back to Liquid and confirm with the user. - Open only the necessary leaf files; use a section
INDEX.mdonly for orientation and discovery. - Prefer examples and ready-to-copy patterns.
Evidence rules
- Prefer repo evidence over assumptions: active theme, base theme,
placement.json, and existing templates. - Trace the shape model first when it is unclear; use
references/TASK-MAP.mdto find shape tracing guidance and ask the user if needed. - Confirm unknown part/field properties in
ContentDefinition.json(orOrchardCore.db) and the relevant field references. - Ask for missing identifiers (content type, part name, field name, display type) instead of inventing them.
- Do not invent recipe steps or feature IDs; use
references/TASK-MAP.mdto find the right recipe references.
Scripts
Use these scripts instead of hand-building extracts.
scripts/extract-content-definitions.pyto extract content types/parts/fields fromContentDefinition.jsonorOrchardCore.db, with optional related-type expansion and Markdown/JSON output. Seereferences/50-content-model/CONTENT-DEFINITIONS-EXTRACTOR.md.scripts/extract-content-items.pyto get content items fromOrchardCore.db, filter by type/IDs/text, and optionally emit a recipecontentstep or a Markdown/JSON extract. Seereferences/50-content-model/CONTENT-ITEMS-EXTRACTOR.md.scripts/generate-orchard-ids.pyto generate Orchard Core IDs that match theDefaultIdGeneratoralphabet for stableContentItemIdvalues in recipes. Seereferences/70-recipes/ID-GENERATION.md.scripts/sync-skill.pyto refresh the entire skill folder from the Lombiq/Orchard-Core-Agent-Skills repo (references, scripts, SKILL.md, assets). The running script is not overwritten until the next sync.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/10-understand-structure/CREATE-THEME.md 3.6 KB
- references/10-understand-structure/INDEX.md 597 B
- references/10-understand-structure/LAYOUTS-ZONES.md 1.6 KB
- references/10-understand-structure/SOLUTION-STRUCTURE.md 3.1 KB
- references/10-understand-structure/THEME-STRUCTURE.md 1.5 KB
- references/20-shapes-placement/ALTERNATES.md 4.0 KB
- references/20-shapes-placement/FORMS-WIDGETS.md 3.9 KB
- references/20-shapes-placement/INDEX.md 1.0 KB
- references/20-shapes-placement/MENU-SHAPES.md 6.0 KB
- references/20-shapes-placement/PAGER-SHAPES.md 5.2 KB
- references/20-shapes-placement/PLACEMENT.md 3.1 KB
- references/20-shapes-placement/SHAPE-WORKFLOW.md 4.3 KB
- references/20-shapes-placement/SHAPES.md 1.2 KB
- references/30-razor/INDEX.md 971 B
- references/30-razor/ORCHARD-HELPER.md 2.6 KB
- references/30-razor/TAG-HELPERS-CACHING.md 598 B
- references/30-razor/TAG-HELPERS-CONTENT-MENUS.md 884 B
- references/30-razor/TAG-HELPERS-MEDIA.md 1014 B
- references/30-razor/TAG-HELPERS-RESOURCES.md 1.3 KB
- references/30-razor/TAG-HELPERS-SHAPES.md 2.6 KB
- references/30-razor/TAG-HELPERS-UTILITIES.md 1.5 KB
- references/30-razor/TAG-HELPERS.md 391 B
- references/40-liquid/INDEX.md 481 B
- references/40-liquid/LIQUID-FILTERS.md 4.6 KB
- references/40-liquid/LIQUID-SHAPES.md 1.2 KB
- references/40-liquid/LIQUID-TAGS.md 4.1 KB
- references/40-liquid/LIQUID.md 1.2 KB
- references/50-content-model/CONTAINERS.md 3.1 KB
- references/50-content-model/CONTENT-DEFINITIONS-EXAMPLES.md 5.5 KB
- references/50-content-model/CONTENT-DEFINITIONS-EXTRACTOR.md 2.1 KB
- references/50-content-model/CONTENT-DEFINITIONS.md 4.2 KB
- references/50-content-model/CONTENT-ITEMS-EXTRACTOR.md 1.9 KB
- references/50-content-model/CONTENT-ITEMS.md 2.0 KB
- references/50-content-model/FIELDS.md 6.6 KB
- references/50-content-model/INDEX.md 1.2 KB
- references/50-content-model/PARTS.md 3.9 KB
- references/50-content-model/SETTINGS.md 2.1 KB
- references/60-assets-resources/INDEX.md 278 B
- references/60-assets-resources/RESOURCES.md 2.6 KB
- references/60-assets-resources/STATIC-FILES.md 774 B
- references/70-recipes/ADMIN-MENU.md 2.7 KB
- references/70-recipes/BASE-RECIPES.md 2.9 KB
- references/70-recipes/FEATURE-CATALOG-ALL.md 4.2 KB
- references/70-recipes/FEATURE-CATALOG.md 1.3 KB
- references/70-recipes/ID-GENERATION.md 761 B
- references/70-recipes/INDEX.md 3.4 KB
- references/70-recipes/RECIPE-COMMANDS.md 886 B
- references/70-recipes/RECIPE-CONTENT.md 3.2 KB
- references/70-recipes/RECIPE-EXAMPLES-CONTENT.md 3.6 KB
- references/70-recipes/RECIPE-EXAMPLES-SETUP.md 5.3 KB
- references/70-recipes/RECIPE-EXAMPLES-WORKFLOWS.md 8.5 KB
- references/70-recipes/RECIPE-EXAMPLES.md 262 B
- references/70-recipes/RECIPE-STEPS-CONTENT-MEDIA.md 1.4 KB
- references/70-recipes/RECIPE-STEPS-CORE.md 1.4 KB
- references/70-recipes/RECIPE-STEPS-DEFINITIONS.md 1022 B
- references/70-recipes/RECIPE-STEPS-MISC.md 1.0 KB
- references/70-recipes/RECIPE-STEPS-SEARCH.md 1.4 KB
- references/70-recipes/RECIPE-STEPS-SECURITY.md 840 B
- references/70-recipes/RECIPE-STEPS-TEMPLATES-WORKFLOWS.md 513 B
- references/70-recipes/RECIPE-STEPS.md 1.1 KB
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.
- 12d ago First seen · 70 lines · 67 tokens per session scan A d41fc5268834
orchard-core-theming is a skill published in the GitHub repository Lombiq/Orchard-Core-Agent-Skills (8 stars, last pushed 7mo ago), licensed BSD-3-Clause. It adds 67 tokens to every session and 1,082 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 skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.