What is authoring-plugins?

A guide to building and distributing add-ons for Claude Code. These add-ons can contain reusable skills, helper agents, commands, event hooks, or connections to outside tools.

Use it to create or update plugin manifests, skills, agents, hooks, commands, marketplace entries, or tool-server integrations.

It explains how to choose the right add-on structure and arrange the required files. This reduces mistakes when creating, revising, or publishing a plugin.

authoring-plugins — Skill for Claude Code by xdg/xdg-claude

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add xdg/xdg-claude

Claude Code

/plugin install plugin-authoring

Made for: Claude Code.

Or install plugin-authoring, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xdg/xdg-claude/authoring-plugins/github.svg)](https://agentmods.dev/skills/xdg/xdg-claude/authoring-plugins)

Your own site

<a href="https://agentmods.dev/skills/xdg/xdg-claude/authoring-plugins"><img src="https://agentmods.dev/badge/skills/xdg/xdg-claude/authoring-plugins/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/xdg/xdg-claude/authoring-plugins"><img src="https://agentmods.dev/badge/skills/xdg/xdg-claude/authoring-plugins.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,325 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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.01325
Opus 5.5	$0.00025	$0.00530
Sonnet 5.5	$0.00012	$0.00265
Haiku 4.5	$0.00006	$0.00133

Measured 1mo ago against content hash 56c2f00c0860, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

authoring-plugins 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 1mo 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.

plugin-authoring/skills/authoring-plugins/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authoring Claude Code plugins

A plugin is a Git-packaged collection of skills, agents, commands, hooks, and MCP servers, installed with /plugin. This skill is the decision layer; the bulky how-to lives in reference/, loaded only for the branch you hit.

Component types

Skills -- user- or model-invoked capabilities. skills/<name>/SKILL.md plus optional scripts/, reference/, assets/. Lazily loaded. The default surface for new work.
Agents (subagents) -- specialized assistants with isolated context and their own tools. agents/<name>.md. Routed to via skill frontmatter (agent) or the Agent tool.
Commands (legacy) -- commands/*.md. Merged into skills as of Claude Code 2.1.3; prefer skills/.
Hooks -- shell commands at lifecycle events. hooks/hooks.json (+ optional hooks/references/). Validate, block, or inject context.
MCP servers -- external tool/service integrations via .mcp.json.

Critical: all component directories sit at plugin root, NOT inside .claude-plugin/.

plugin-name/
├── .claude-plugin/plugin.json   # required manifest
├── skills/<name>/SKILL.md       # + scripts/ reference/ assets/
├── agents/<name>.md
├── hooks/hooks.json             # + references/
└── .mcp.json

Skills, agents, and hooks under their standard dirs are auto-discovered -- no manifest entry needed.

Progressive disclosure

Skills load in three levels; this is the whole reason they beat always-on CLAUDE.md content:

Metadata (always loaded, ~100 words) -- name + description. Enough for Claude to know when to reach for the skill.
SKILL.md body (loaded on trigger, target <5k words) -- procedure and guidance.
Bundled resources (loaded on demand) -- scripts/ run without entering context, reference/ read only when needed, assets/ used in output.

Keep SKILL.md lean; push depth into reference/. If a reference exceeds ~10k words, put grep patterns in SKILL.md so Claude can target it.

The three skill patterns (decide before writing files)

Read the full file on GitHub · 75 lines

Files

What ships with it

6 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.

1mo ago Changed 56c2f00c0860
2mo ago First seen · 75 lines · 62 tokens per session scan A 9be38e11d3f4

Subscribe to this mod's changes

authoring-plugins is a skill published in the GitHub repository xdg/xdg-claude (20 stars, last pushed 6d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,325 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 2026-08-30.

Building agents

authoring-plugins next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
authoring-pluginsxdg/xdg-claude	Skill	20	6d ago	Apache-2.0	A	62	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code