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.
npx agentmods add skills/mumudevx/claude-plugin-builder/building-pluginsnpx skills add mumudevx/claude-plugin-builder --skill building-pluginsgit clone --depth 1 https://github.com/mumudevx/claude-plugin-builderWrote 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/mumudevx/claude-plugin-builder/building-plugins)<a href="https://agentmods.dev/skills/mumudevx/claude-plugin-builder/building-plugins"><img src="https://agentmods.dev/badge/skills/mumudevx/claude-plugin-builder/building-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 | $0.00054 | $0.02667 |
| Opus 5 | $0.00027 | $0.01333 |
| Sonnet 5 | $0.00011 | $0.00533 |
| Haiku 4.5 | $0.00005 | $0.00267 |
Grade A, and why
building-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 3d 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building Plugins
A Claude Code plugin is a distributable package of skills, commands, agents, hooks, MCP servers, and LSP servers that extends Claude's capabilities. This skill guides you through the complete plugin creation lifecycle: brainstorming requirements, designing architecture, scaffolding the project, implementing components, and distributing the result.
HARD-GATE
Do NOT scaffold or write any plugin code until brainstorming and design are COMPLETE and the user has approved the plan. Jumping to implementation without understanding requirements leads to rework. The process is: Understand → Design → Approve → Scaffold → Implement → Validate.
Checklist
Use TaskCreate to track each step:
- Understand requirements — brainstorm with the user to clarify what the plugin should do, who it's for, and what problems it solves
- Choose components — use the Component Decision Guide to determine which plugin components are needed
- Design and approve — present the plugin design (name, structure, components) and get user approval
- Write implementation plan — detail each file to create, its purpose, and content outline
- Scaffold plugin structure — create directories and plugin.json
- Implement components — write each component following reference docs
- Validate and test — verify structure, test with
claude --plugin-dir - Distribute (optional) — publish to marketplace or share
Process Flow
digraph plugin_flow {
rankdir=TB;
node [shape=box, style=rounded];
start [label="User wants a plugin", shape=doublecircle];
brainstorm [label="1. Brainstorm\nWhat does it do?\nWho is it for?"];
components [label="2. Choose Components\nSkills? Commands? Hooks?\nAgents? MCP? LSP?"];
design [label="3. Design Review\nPresent structure to user"];
approve [label="User approves?", shape=diamond];
plan [label="4. Implementation Plan\nFile-by-file detail"];
scaffold [label="5. Scaffold\nDirectories + plugin.json"];
implement [label="6. Implement\nWrite each component"];
validate [label="7. Validate\nStructure + load test"];
distribute [label="8. Distribute\n(optional)"];
done [label="Plugin ready", shape=doublecircle];
revise [label="Revise design"];
start -> brainstorm;
brainstorm -> components;
components -> design;
design -> approve;
approve -> plan [label="yes"];
approve -> revise [label="no"];
revise -> brainstorm;
plan -> scaffold;
scaffold -> implement;
implement -> validate;
validate -> distribute;
distribute -> done;
}
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.
- 3d ago First seen · 268 lines · 54 tokens per session scan A 9d76984ecf0b
building-plugins is a skill published in the GitHub repository mumudevx/claude-plugin-builder (7 stars, last pushed 6mo ago), licensed MIT. It adds 54 tokens to every session and 2,667 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 2026-08-31.
Other skills, from other repositories
plugin-sdk-patterns
Unified patterns and templates for creating consistent Claude Code plugins. Use when creating new plugins, designing plugin architecture, implementing builder patterns, or standardizing plugin structure. Trigger keywords - "plugin SDK", "plugin template", "plugin pattern", "builder pattern", "plugin structure", "new…
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约,产出 UI-DESIGN.md。四端通用。.
taiyi-evolve
TaiyiForge 辅助 — 实现后架构与文档同步(architecture-sync)。OpenCode / Claude / Codex / Cursor 通用。.
taiyi-diagram-c4
TaiyiForge 辅助 — 从代码反推 C4 架构文档(Observed/Inferred 分层 · Mermaid 真源)。OpenCode / Claude / Codex / Cursor 通用。.
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.
steer
Project-profile recalibration. Audits session calibration drift, presents per-cluster evidence for a user verdict, writes the updated project-profile rule, and inscribes a settled-direction clause.