jekyll

jekyll is a skill for Claude Code, Codex from n-n-code/n-n-code-skills. It costs 97 tokens per session (1,116 once invoked), scanned A, original, MIT.

A skill for building and maintaining Jekyll sites, which turn templates and content into static web pages served without a running application server.

In plain words
What is it for?
It helps work with Liquid templates, page layouts, reusable includes, collections, themes, front matter, assets, and conversions from static HTML.
Why use it?
It gives a structured way to explain, design, implement, or troubleshoot Jekyll pages while keeping unrelated site work unchanged.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit It helps work with Liquid templates, page layouts, reusable includes, collections, themes, front matter, assets, and conversions from static HTML.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/n-n-code/n-n-code-skills/jekyll
Install

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.

Any agent
npx skills add n-n-code/n-n-code-skills --skill jekyll
Clone the repo
git clone --depth 1 https://github.com/n-n-code/n-n-code-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for jekyll

README.md
[![agentmods](https://agentmods.dev/badge/skills/n-n-code/n-n-code-skills/jekyll.svg)](https://agentmods.dev/skills/n-n-code/n-n-code-skills/jekyll)
Your own site
<a href="https://agentmods.dev/skills/n-n-code/n-n-code-skills/jekyll"><img src="https://agentmods.dev/badge/skills/n-n-code/n-n-code-skills/jekyll.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.01116
Opus 5 $0.00048 $0.00558
Sonnet 5 $0.00019 $0.00223
Haiku 4.5 $0.00010 $0.00112

Measured today against content hash 867255ffd4f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

jekyll 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.

.agents/skills/jekyll/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jekyll

Use standard Jekyll to turn content and templates into maintainable static pages. Keep the workflow independent of a particular theme, host, agent, CSS framework, or frontend toolchain.

Choose the activity

  • Explain or review: explain concepts, trace supplied sources, or report evidence-backed findings; keep files unchanged.
  • Design: propose the content structure, layout, reusable pieces, visual direction, and URLs in the response unless a durable artifact is requested. A proposal alone does not authorize implementation.
  • Implement: create, change, redesign, or convert the requested pages and relevant source files, preserving unrelated work.
  • Troubleshoot: isolate the failing source, configuration, or runtime seam. Diagnosis alone stays read-only; fix requests authorize relevant remediation.

Infer the activity from the request and existing authorization. Ask only about unresolved choices that materially affect the result; reuse existing approval.

For a conceptual question without a site-specific dependency, answer directly with the relevant Jekyll explanation and a small native example when useful. Do not require a repository, inspect the environment, or ask for project files merely to explain layouts, includes, collections, or URLs. Use applicable official documentation for version-sensitive details; distinguish an example from a claim about a site you have not inspected.

Inspect a site when the task needs one

  1. Read applicable instructions and working-tree changes. Locate the source and relevant configuration, dependencies, and content. Establish Jekyll from the explicit target or project evidence; Liquid or GitHub Pages alone is insufficient. Check installed versions where they affect the request.
  2. Follow the touched page's layouts, includes, data, styles, and assets. Inspect the active theme before declaring a locally absent template missing. Expand investigation only to resolve a relevant uncertainty; inspect hosting and external tooling only when they affect the task.
  3. Trace the required source-to-output path, or map it for a new page. Choose native content and presentation structures suited to the purpose, preserving established URLs and visual choices unless changing them is requested.
  4. Return findings or a proposal, or make scoped source edits for implementation. Reuse meaningful shared layouts, includes, and data; preserve selectors and interactions when converting HTML. A new site can use ordinary Jekyll directories and HTML/CSS without an additional toolchain.
  5. Verify at the task's scale. Before building or serving, read the build reference and inspect the configured destination. Check generated content, links, and assets; use available browser capabilities for visual changes. Build success alone does not establish visual correctness.

Read the full file on GitHub · 96 lines

Files

What ships with it

4 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.

Changes

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.

  1. today First seen · 96 lines · 97 tokens per session scan A 867255ffd4f4

Subscribe to this mod's changes

jekyll is a skill published in the GitHub repository n-n-code/n-n-code-skills (4 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 1,116 once invoked, about $0.0005 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 2026-09-06.

Related

Other skills, from other repositories

web-frontend-designer

Scaffold frontend architecture, components, routing, and UI dependencies from project config and wireframes.

0x-Professor/Agent-Skills-Hub · 25 tokens

web-frontend-tester

Run frontend functional, accessibility, visual, and performance test planning with structured reports.

0x-Professor/Agent-Skills-Hub · 22 tokens

baoyu-markdown-to-html

Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, Mermaid (rendered to PNG via headless Chrome), PlantUML, footnotes, alerts, infographics, and optional bottom citations for external links. Use when user asks for "markdown to html", "convert md to html", "md 转 html"…

JimLiu/baoyu-skills · 94 tokens

frontend-specialist

A front-end development workflow for building or improving web pages, components, layouts, forms, dashboards, and responsive interfaces. It covers common tools and frameworks such as React, Vue, Next.js, Tailwind, and CSS.

huangwb8/skills · 61 tokens

migrate-divi-to-breakdance

Use when the user says 'migrate divi to breakdance', 'convert divi to breakdance', or 'rebuild divi pages in breakdance'. Parses Divi shortcodes, maps modules to Breakdance elements, and creates draft duplicates for review.

respira-press/agent-skills-wordpress · 61 tokens

migrate-divi-to-bricks

Use when the user says 'migrate divi to bricks', 'convert divi to bricks', or 'rebuild divi pages in bricks'. Parses Divi shortcode content, maps modules to Bricks elements, and generates draft duplicates for review.

respira-press/agent-skills-wordpress · 58 tokens