Skills Plugin Structure
📦

Plugin Structure

v0.1.0 Content revision r1 Safe ⚙️ External commands🌐 Network access📁 Filesystem access🔑 Env variables

Build Claude Code Plugin Structure

Plugin authors need consistent layouts that Claude Code can discover. This skill explains manifests, components, hooks, MCP servers, and portable paths for reliable plugins.

Supports: Claude Codex Code(CC)
🥈 80 Silver

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "Plugin Structure" from https://skillstore.io/skills/anthropics-plugin-structure.md and its manifest at https://skillstore.io/api/skills/anthropics-plugin-structure/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/anthropics-plugin-structure.md Signed manifest GET /api/skills/anthropics-plugin-structure/manifest Signed lockfile GET /api/skills/anthropics-plugin-structure/lockfile

Test it

Using "Plugin Structure". Create a small plugin for a reusable review command.

Expected outcome:

  • A minimal folder plan with the manifest under .claude-plugin.
  • A command file location and a short explanation of how Claude Code discovers it.
  • Naming and path guidance for future components.

Using "Plugin Structure". Organize a team plugin with commands, agents, and skills.

Expected outcome:

  • A structured component map for commands, agents, skills, hooks, scripts, and references.
  • Clear boundaries between user-facing commands and reusable knowledge files.
  • Notes about portable path references and optional custom manifest paths.

Using "Plugin Structure". Audit a proposed plugin tree before publishing.

Expected outcome:

  • A checklist of missing required files and misplaced components.
  • Specific corrections for manifest paths, file names, and nested directories.
  • A short readiness summary for Claude Code discovery.

Security Audit

Safe
v8 • 7/18/2026 Open versioned report

All 218 static findings are false positives caused by Markdown code fences, inline code, placeholder metadata, or non-executing examples. The reviewed files contain documentation only, with no credential harvesting, network exfiltration, prompt injection, or hidden behavior. Some examples describe hooks, MCP servers, and shell commands that generated plugins should review before use.

7
Files scanned
3,146
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (50)
examples/advanced-plugin.md:198 examples/advanced-plugin.md:204 examples/advanced-plugin.md:285-286 examples/advanced-plugin.md:286-287 examples/advanced-plugin.md:287-292 examples/advanced-plugin.md:292 examples/advanced-plugin.md:295 examples/advanced-plugin.md:300 examples/advanced-plugin.md:307 examples/advanced-plugin.md:383 examples/advanced-plugin.md:389 examples/advanced-plugin.md:396 examples/advanced-plugin.md:399 examples/advanced-plugin.md:428 examples/advanced-plugin.md:436 examples/advanced-plugin.md:444 examples/advanced-plugin.md:458 examples/advanced-plugin.md:468-473 examples/advanced-plugin.md:473 examples/advanced-plugin.md:478-483 examples/advanced-plugin.md:483 examples/advanced-plugin.md:490 examples/advanced-plugin.md:494 examples/advanced-plugin.md:497 examples/advanced-plugin.md:500 examples/advanced-plugin.md:503 examples/advanced-plugin.md:506 examples/advanced-plugin.md:518 examples/advanced-plugin.md:526 examples/advanced-plugin.md:531 examples/advanced-plugin.md:545 examples/advanced-plugin.md:567 examples/advanced-plugin.md:586 examples/advanced-plugin.md:593 examples/advanced-plugin.md:595 examples/advanced-plugin.md:598 examples/advanced-plugin.md:600 examples/advanced-plugin.md:603 examples/advanced-plugin.md:605 examples/advanced-plugin.md:610-611 examples/advanced-plugin.md:611-612 examples/advanced-plugin.md:612-617 examples/advanced-plugin.md:617-618 examples/advanced-plugin.md:618-619 examples/advanced-plugin.md:619-624 examples/advanced-plugin.md:624 examples/advanced-plugin.md:626 examples/advanced-plugin.md:498 examples/standard-plugin.md:80 examples/standard-plugin.md:82
🌐 Network access (17)
examples/advanced-plugin.md:113 examples/advanced-plugin.md:115 examples/advanced-plugin.md:118 examples/standard-plugin.md:50 examples/standard-plugin.md:51 references/manifest-reference.md:97 references/manifest-reference.md:105 references/manifest-reference.md:143 references/manifest-reference.md:152 references/manifest-reference.md:476 references/manifest-reference.md:477 references/manifest-reference.md:495 references/manifest-reference.md:497 references/manifest-reference.md:500 SKILL.md:74 SKILL.md:76 SKILL.md:77
📁 Filesystem access (8)
examples/advanced-plugin.md:141 references/manifest-reference.md:340 references/manifest-reference.md:349 references/manifest-reference.md:301 references/manifest-reference.md:308 references/manifest-reference.md:361 references/manifest-reference.md:517 SKILL.md:96
🔑 Env variables (3)
examples/advanced-plugin.md:170 references/manifest-reference.md:320 SKILL.md:247
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/anthropics-plugin-structure/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/anthropics-plugin-structure/security.svg)](https://skillstore.io/skills/anthropics-plugin-structure?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/anthropics-plugin-structure?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/anthropics-plugin-structure/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/anthropics-plugin-structure.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

anthropics. (2026). Plugin Structure security audit report (audit version 8) [Author version 0.1.0]. Skillstore. https://skillstore.io/skills/anthropics-plugin-structure/audits/8

BibTeX citation

@techreport{anthropics-anthropics-plugin-structure-2026, author = {anthropics}, title = {Plugin Structure security audit report (audit version 8)}, institution = {Skillstore}, year = {2026}, number = {8}, url = {https://skillstore.io/skills/anthropics-plugin-structure/audits/8}, note = {Author version 0.1.0} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "Plugin Structure security audit report (audit version 8)" version: "0.1.0" type: report authors: - name: "anthropics" date-released: "2026-07-18" url: "https://skillstore.io/skills/anthropics-plugin-structure/audits/8" identifiers: - type: other value: "skillstore:anthropics-plugin-structure:audit:8" description: "Skillstore immutable audit report identifier"

Compare variants

3 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Higher Skillstore usage
anthropics Recommended

plugin-structure

Skillstore Score 80
Evidence Confidence High
Skillstore usage 10
Updated

2026-08-21

anthropics Current

anthropics-plugin-structure

Skillstore Score 80
Evidence Confidence High
Skillstore usage 8
Updated

2026-08-21

davila7

davila7-plugin-structure

Skillstore Score 79
Evidence Confidence High
Skillstore usage 7
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
100
Maintainability
87
Content
77
Community
74
Spec Compliance

What You Can Build

Scaffold a first plugin

Create a minimal plugin layout with the required manifest and starter component directories.

Standardize team plugins

Define consistent folders, naming rules, and manifest conventions for shared plugin repositories.

Review complex plugin architecture

Check a plugin design that combines commands, agents, skills, hooks, scripts, and MCP servers.

Try These Prompts

Create a minimal plugin 
Create a minimal Claude Code plugin named my-helper with the required manifest and one command. Explain each file purpose.
Organize plugin components 
Design a plugin layout for code quality automation with commands, agents, skills, scripts, and references. Use standard discovery paths.
Plan hooks and MCP servers 
Plan a plugin that uses hooks and MCP servers. Include safe path references, environment variables, and component boundaries.
Review an existing structure 
Review this plugin file tree for Claude Code compatibility. Identify manifest, discovery, naming, portability, and maintainability issues.

Best Practices

  • Keep component directories at the plugin root unless a custom path is necessary.
  • Use CLAUDE_PLUGIN_ROOT for paths that reference files inside the plugin.
  • Create only the component directories the plugin actually needs.

Avoid

  • Putting commands, agents, skills, or hooks inside .claude-plugin.
  • Using absolute paths, home directory shortcuts, or parent directory traversal in manifest paths.
  • Creating broad utility folders without clear component ownership or documentation.

Frequently Asked Questions

What does this skill help create?
It helps design Claude Code plugin folders, manifests, components, hooks, MCP server references, and portable paths.
Does it install plugins?
No. It provides structure guidance and examples, but it does not install or enable plugins.
Can it create hooks?
It can explain where hook configuration belongs and how hook scripts should be referenced safely.
Does it support MCP servers?
Yes. It documents where MCP server configuration belongs and how manifests can reference it.
Is it only for new plugins?
No. It can also review existing plugin trees for discovery, naming, and portability issues.
Which tools can use it?
The report marks support for Claude, Codex, and Claude Code.

Developer Details

Author

anthropics

License

MIT

Author version

v0.1.0

Skillstore revision

r1

Repository

https://github.com/anthropics/claude-plugins-official/tree/main/plugins/plugin-dev/skills/plugin-structure

Ref

1b5b6c4962b2ad5a7a34603cab2685bbbd1b61ef

Maintenance freshness

7/18/2026

Usage

6 downloads · 636 views

File structure

📁 examples/

📄 advanced-plugin.md

📄 minimal-plugin.md

📄 standard-plugin.md

📄 README.md

📁 references/

📄 component-patterns.md

📄 manifest-reference.md

📄 SKILL.md

More from anthropics

View all

Related Skills

View all