distribute-plugins

distribute-plugins is a skill for Claude Code from Vibe-Marketer/plugins-and-skills. It costs 122 tokens per session (2,108 once invoked), scanned A, original, MIT.

A release workflow for Claude Code plugins, which are add-ons that extend Claude Code. It checks a plugin, assigns a semantic version, packages it, and prepares it for distribution.

In plain words
What is it for?
Use it to validate, version, package, document, and publish Claude Code plugins through GitHub releases, a marketplace, or a local path.
Why use it?
It reduces the risk of publishing broken plugins, leaking secrets, or producing packages that fail on a clean install. Semantic versions also tell users whether a release contains fixes, new features, or breaking changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Claude Code.

Part of the create-plugins plugin — 12 skills, 6 commands, 9 agents shipped together

Good fit Use it to validate, version, package, document, and publish Claude Code plugins through GitHub releases, a marketplace, or a local path.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vibe-marketer/plugins-and-skills/distribute-plugins
Install

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.

Any agent
npx skills add Vibe-Marketer/plugins-and-skills --skill distribute-plugins
Clone the repo
git clone --depth 1 https://github.com/Vibe-Marketer/plugins-and-skills

Made for: Claude Code.

Or install create-plugins, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 9 agents.

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.

agentmods badge for distribute-plugins

README.md
[![agentmods](https://agentmods.dev/badge/skills/vibe-marketer/plugins-and-skills/distribute-plugins.svg)](https://agentmods.dev/skills/vibe-marketer/plugins-and-skills/distribute-plugins)
Your own site
<a href="https://agentmods.dev/skills/vibe-marketer/plugins-and-skills/distribute-plugins"><img src="https://agentmods.dev/badge/skills/vibe-marketer/plugins-and-skills/distribute-plugins.svg" alt="Measured on agentmods" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,108 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00122 $0.02108
Opus 5 $0.00061 $0.01054
Sonnet 5 $0.00024 $0.00422
Haiku 4.5 $0.00012 $0.00211

Measured 7d ago against content hash 2c36aaf3df21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

distribute-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 7d 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.

create-plugins/skills/distribute-plugins/SKILL.md · 284 lines

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.

<essential_principles>

  1. Validate Before Publishing. Never distribute a plugin that hasn't passed structural validation and skill audits. Broken plugins damage trust and are hard to unpublish.

  2. Semantic Versioning. Version numbers communicate intent. MAJOR for breaking changes. MINOR for new features. PATCH for fixes. Users depend on this contract.

  3. No Secrets in Distribution. Hardcoded paths, credentials, API keys, and personal data must be caught before packaging. One leaked secret in a published plugin is a security incident.

  4. Reproducible Installs. Every published version must install cleanly from the distribution source. If it works on your machine but not on a clean install, it's not ready.

</essential_principles>

<quick_start>

  1. Point to the plugin directory
  2. Pre-distribution checks run automatically (audit, validation, secrets scan)
  3. Choose the version bump type (major, minor, patch)
  4. Package is built (excluding dev files)
  5. Choose distribution method (GitHub release, marketplace, path install)
  6. Publish with documentation </quick_start>

<step_1> Pre-Distribution Checklist

Run all checks before packaging. Every item must pass:

# Check How to Verify
D01 All skills pass audit Run audit-extensions on each skill
D02 plugin.json is valid Parse JSON, verify required fields
D03 plugin.json has license field Must specify a license (MIT, Apache-2.0, etc.)
D04 README.md exists Must include installation instructions
D05 No hardcoded absolute paths Grep for /Users/, /home/, C:\ patterns
D06 No credentials or secrets Grep for API_KEY, SECRET, TOKEN, password patterns
D07 No .env files included Check for .env, .env.local, .env.production
D08 All references resolve Every file referenced in SKILL.md routing/index exists
D09 All skill names match directories YAML name field = directory name for every skill
D10 No empty skill directories Every skill dir has a SKILL.md with content

If any check fails, report the failures and stop. Do not proceed to packaging with known issues. </step_1>

<step_2> Semantic Versioning

Determine the version bump based on changes since last release:

MAJOR version (X.0.0) -- Breaking changes:

  • Renamed or removed skills
  • Changed skill behavior that users depend on
  • Removed commands or subagents
  • Changed plugin.json structure
  • Renamed the plugin itself

MINOR version (x.Y.0) -- New features:

  • Added new skills
  • Added new workflows to existing skills
  • Added new commands or subagents
  • Added new references or templates
  • New configuration options

PATCH version (x.y.Z) -- Fixes:

  • Bug fixes in skill content
  • Typo corrections
  • Updated references for accuracy
  • Performance improvements
  • Documentation updates

Version file: Update the version field in plugin.json.

If no previous version exists, start at 1.0.0.

Changelog: Generate or update CHANGELOG.md with:

## [X.Y.Z] - YYYY-MM-DD

### Added
- [New features]

### Changed
- [Modified features]

### Fixed
- [Bug fixes]

### Removed
- [Removed features]

</step_2>

<step_3> Packaging

Create the distribution package:

Exclude from package:

  • __pycache__/
  • node_modules/
  • *.pyc
  • .DS_Store
  • evals/ (test data, not runtime)
  • .env*
  • .git/
  • *.log
  • .claude/ (user-specific config)
  • *.tmp
  • *.bak

Include in package:

  • plugin.json (root manifest)
  • skills/ (all skill directories with SKILL.md, workflows/, references/, templates/, scripts/)
  • agents/ (all subagent configurations)
  • commands/ (all slash commands)
  • hooks/ (all hook configurations)
  • scripts/ (plugin-level scripts)
  • shared/ (shared rules, templates, configs)
  • README.md
  • LICENSE
  • CHANGELOG.md

Read the full file on GitHub · 284 lines

Files

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.

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.

  1. 7d ago First seen · 284 lines · 122 tokens per session scan A 2c36aaf3df21

Subscribe to this mod's changes

distribute-plugins is a skill published in the GitHub repository Vibe-Marketer/plugins-and-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 122 tokens to every session and 2,108 once invoked, about $0.0006 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.