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 MadAppGang/magus/plugin install devWrote 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/madappgang/magus/plugin-sdk-patterns)<a href="https://agentmods.dev/skills/madappgang/magus/plugin-sdk-patterns"><img src="https://agentmods.dev/badge/skills/madappgang/magus/plugin-sdk-patterns/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/madappgang/magus/plugin-sdk-patterns"><img src="https://agentmods.dev/badge/skills/madappgang/magus/plugin-sdk-patterns.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 | $0.00044 | $0.03892 |
| Opus 5.5 | $0.00018 | $0.01557 |
| Sonnet 5.5 | $0.00009 | $0.00778 |
| Haiku 4.5 | $0.00004 | $0.00389 |
Grade A, and why
plugin-sdk-patterns 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 22d 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.
This is a copy
91% identical to plugin-sdk-patterns — 1,172 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building a Claude Code plugin that loads
Plugins fail quietly. A manifest in the wrong folder, a frontmatter key the loader does not
read, or a hook that exits 1 leaves every file looking right while the component does
nothing. For a skill that exists on disk but did not register, the loader answers
Unknown skill: <plugin>:<name>, the same string it gives for a typo. This file holds the
facts that decide whether each part of a plugin loads and behaves as written.
Done means claude plugin list shows the plugin loaded with no error, and every
component you touched did its job once in a real session (section 7).
If the repo you are working in has its own plugin standard, that standard wins where it differs from this file. In the Magus marketplace source repo, also read section 8.
1. Directory structure
my-plugin/
├── .claude-plugin/
│ └── plugin.json # the manifest; the only file that belongs in this folder
├── skills/
│ └── <skill-name>/
│ ├── SKILL.md
│ └── references/ # optional depth, opened only on an explicit instruction
├── commands/
│ └── <command>.md
├── agents/
│ └── <agent>.md
├── hooks/
│ └── hooks.json
├── .mcp.json # MCP servers, if the plugin ships any
└── README.md # for people; nothing loads it
- The manifest lives at
.claude-plugin/plugin.json. Aplugin.jsonat the plugin root is consulted at install time only; the runtime loader never reads it. Theskills,dependenciesandmcpServersit declares do nothing, the plugin falls back to scanning its default folders, and every nested skill it lists answersUnknown skill. - Only
plugin.jsongoes inside.claude-plugin/. Every component folder sits at the plugin root. - Folders the loader does not know, such as
mcp-servers/orexamples/, are never read. - A plugin cannot reach outside its own directory. A
../sharedcomponent path is rejected, and files above the plugin root are not copied into the install cache, so a script that reads them works in your checkout and fails once installed. - Component paths are relative to the plugin root, start with
./, and use forward slashes.
What ships with it
2 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.
- 22d ago Changed · -745 lines · +8 tokens per session 20dda0202150
- 1mo ago Changed 7c5fc400761e
- 1mo ago First seen · 1,029 lines · 36 tokens per session scan A 44a555f10f9d
plugin-sdk-patterns is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 3,892 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to plugin-sdk-patterns, differing in 1,172 lines, and is treated as a copy.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…