manual

manual is a skill for Claude Code, Codex from aimeos/pagible. It costs 57 tokens per session (995 once invoked), scanned A, original, MIT.

A documentation page design system for software projects. It defines layouts and reusable elements such as navigation, code blocks, callouts, tables, and light and dark themes.

In plain words
What is it for?
Use it to design developer documentation pages with sidebars, page outlines, code-copy buttons, numbered instructions, reference tables, version badges, and repository links.
Why use it?
It gives technical documentation a consistent structure and makes pages easier to read and navigate. It also separates setup guides, task guides, reference pages, and change logs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to design developer documentation pages with sidebars, page outlines, code-copy buttons, numbered instructions, reference tables, version badges, and repository links.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aimeos/pagible/manual
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 aimeos/pagible --skill manual
Clone the repo
git clone --depth 1 https://github.com/aimeos/pagible

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 manual

README.md
[![agentmods](https://agentmods.dev/badge/skills/aimeos/pagible/manual/github.svg)](https://agentmods.dev/skills/aimeos/pagible/manual)
Your own site
<a href="https://agentmods.dev/skills/aimeos/pagible/manual"><img src="https://agentmods.dev/badge/skills/aimeos/pagible/manual/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.

agentmods 80×15 button for manual

Your own site · 80×15
<a href="https://agentmods.dev/skills/aimeos/pagible/manual"><img src="https://agentmods.dev/badge/skills/aimeos/pagible/manual.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 995 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 $0.00057 $0.00995
Opus 5.5 $0.00023 $0.00398
Sonnet 5.5 $0.00011 $0.00199
Haiku 4.5 $0.00006 $0.00100

Measured 4d ago against content hash 5b64f43757fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

manual 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 4d 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.

themes/manual/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manual Theme Design System

Direction

Write documentation like the best developer docs (Stripe, Tailwind CSS, Laravel, Starlight): each page answers one question, starts with what the reader will achieve and gets them to working code as fast as possible. Organize the content into four kinds of pages and don't mix them. Getting started pages take a new user from install to first success. Guides solve one practical task. Reference pages list every class, option and command. The changelog records what changed. Keep the design quiet so the text and code carry the page; don't use decorative images, stock photos or marketing claims inside the docs.

Foundations

  • Use only the markup and classes supplied by ./theme/views/ and the theme's code, text, docs and main views.
  • Use system sans-serif and monospace fonts and the existing --pico-* variables.
  • Use slate neutrals (#0F172A, #334155, #64748B, #E2E8F0) for text and borders and blue (#2563EB, #60A5FA in dark mode) for links and the active page; code blocks always stay dark.
  • Support light and dark mode; never place fixed light colors on themeable backgrounds.
  • Use 0.5rem corners and thin borders instead of shadows.

Structure

  • Home (page): a hero with the one-line promise and "Get started" button, a short code sample, feature cards with white line icons, cards linking to the sections and a cta.
  • Sections (docs) directly below home, e.g. "Docs", "API reference" and "Changelog"; each becomes a top-level header link and the root of its sidebar.
  • Groups below a section, e.g. "Getting started" and "Guides", each with a short overview listing its pages; topics go below the groups. Don't nest deeper than this, the sidebar shows two levels.
  • The order in the tree is the reading order; the previous and next links follow it.

Components

  • Headings: use heading elements with level 2 for sections and 3 for methods or sub-steps; they build the "On this page" outline and get anchor links. Never skip a level and keep them short ("Install the package", add(name, data, options?)).
  • Text: short paragraphs, inline code for every identifier, file name and value, and lists for options and steps.
  • Callouts: use GitHub alerts in text elements. Use [!NOTE] for context, [!TIP] for shortcuts, [!IMPORTANT] for required steps, [!WARNING] for risky actions and [!CAUTION] for data loss. Use at most two per page.
  • Code: one code element per runnable snippet with the language set, at most about 15 lines, complete enough to copy and run. Shell commands use bash and contain no $ prompt.
  • Steps: a vertical timeline with "Step 1", "Step 2" … as labels for installation and setup sequences.
  • Reference tables: table with a header row; columns like Option, Default, Description or Parameter, Type, Description, with values in backticks.
  • Changelog: a vertical timeline with "version · date" labels, newest first, and Markdown bullets starting with Added, Changed, Fixed or Breaking.
  • Project details: the manual::project config adds the version pill, the repository link, the license in the footer and the SoftwareSourceCode JSON-LD.

Read the full file on GitHub · 50 lines

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. 4d ago First seen · 50 lines · 57 tokens per session scan A 5b64f43757fc

Subscribe to this mod's changes

manual is a skill published in the GitHub repository aimeos/pagible (596 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 995 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.

Related

Other skills, from other repositories

api-designer

Designs production-grade APIs — REST, GraphQL, gRPC, and AsyncAPI patterns including pagination, versioning, error handling, rate limiting, and API governance. Use when the user asks to design APIs, create endpoints, build an API layer, write OpenAPI specs, or needs help with REST/GraphQL/gRPC service design.

buiphucminhtam/forgewright · 73 tokens

api-design-first

Design-first API development skill. Generates OpenAPI 3.1 specifications, enforces REST design best practices, validates endpoints, handles versioning, pagination, error formatting, authentication patterns, rate limiting, and idempotency. Activates when users say "design an API", "create OpenAPI spec", "API endpoint"…

JPeetz/agent-skills · 117 tokens

strapi-cms

Customisable headless CMS with Strapi.

bidewio/better-openclaw · 13 tokens

api-design

Applies REST and GraphQL design principles to produce or review an API contract.

MarieLynneBlock/arcanum-artifex · 19 tokens

api-integration-architect

Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.

sickn33/agentic-awesome-skills · 33 tokens

scalar-design-system

Scalar's design system — design tokens, theming (@scalar/themes), CSS variables, and the @scalar/components library. Use when designing or implementing Scalar UI, especially with Paper (code-to-design / design-to-code), so output matches real Scalar tokens, colors, typography, spacing, and components instead of…

scalar/scalar · 68 tokens