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.
/plugin marketplace add xdg/xdg-claude/plugin install plugin-authoringWrote 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/xdg/xdg-claude/authoring-plugins)<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="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 5.1 | $0.00062 | $0.01325 |
| Opus 5 | $0.00031 | $0.00662 |
| Sonnet 5 | $0.00012 | $0.00265 |
| Haiku 4.5 | $0.00006 | $0.00133 |
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 8d 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 — 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.mdplus optionalscripts/,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; preferskills/. - Hooks — shell commands at lifecycle events.
hooks/hooks.json(+ optionalhooks/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)
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.
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.
- 8d ago First seen · 75 lines · 62 tokens per session scan A 9be38e11d3f4
authoring-plugins is a skill published in the GitHub repository xdg/xdg-claude (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 1,325 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…