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.
git clone --depth 1 https://github.com/vmkteam/claude-pluginsWrote 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/plugins/vmkteam/claude-plugins/developer)<a href="https://agentmods.dev/plugins/vmkteam/claude-plugins/developer"><img src="https://agentmods.dev/badge/plugins/vmkteam/claude-plugins/developer/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/plugins/vmkteam/claude-plugins/developer"><img src="https://agentmods.dev/badge/plugins/vmkteam/claude-plugins/developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
vmkteam-developer 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 6d 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.
What it actually says
{
"name": "vmkteam-developer",
"version": "1.3.0",
"description": "vmkteam SDLC developer profile — 35 skills for Go API services: onboarding, task solving, code review, monitoring, incident investigation, skills health check",
"author": {
"name": "vmkteam",
"url": "https://github.com/vmkteam"
},
"homepage": "https://vmkteam.dev",
"repository": "https://github.com/vmkteam/claude-plugins",
"license": "MIT",
"keywords": ["go", "api", "sdlc", "postgresql", "zenrpc", "vmkteam", "code-review", "monitoring", "youtrack"]
}
What it installs
The manifest is a name and a version. 35 skills travel with it, and installing the plugin installs all of them — 1,935 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill go-review A 63 tokens
- Skill gold-arch A 88 tokens
- Skill onboard A 53 tokens
- Skill solve A 65 tokens
- Skill decompose A 46 tokens
- Skill testing A 93 tokens
- Skill incident A 56 tokens
- Skill mfd A 99 tokens
- Skill mr-review A 50 tokens
- Skill colgen A 87 tokens
- Skill gitlab A 51 tokens
- Skill investigate A 61 tokens
- Skill pgmigrator A 30 tokens
- Skill prometheus A 54 tokens
- Skill security A 59 tokens
- Skill zenrpc A 35 tokens
- Skill errors A 55 tokens
- Skill kibana A 44 tokens
- Skill loki A 53 tokens
- Skill pgd A 27 tokens
- Skill skills-check A 40 tokens
- Skill youtrack A 47 tokens
- Skill cron A 71 tokens
- Skill pgmdd A 30 tokens
- Skill rpcgen A 54 tokens
- Skill sentry A 55 tokens
- Skill api-health A 43 tokens
- Skill appkit A 61 tokens
- Skill grafana A 50 tokens
- Skill nomad A 58 tokens
- Skill commit-msg A 45 tokens
- Skill ci-cd A 55 tokens
- Skill embedlog A 51 tokens
- Skill philosophy A 58 tokens
- Skill scaffold C 48 tokens
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.
- 6d ago Changed 9814f4860fff
- 23d ago Changed 0b0f06e03cf2
- 1mo ago First seen · 14 lines scan A 2cdec55f0e1a
vmkteam-developer is a plugin published in the GitHub repository vmkteam/claude-plugins (7 stars, last pushed 6d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
cobra-viper
Definitive guide to building CLI applications with Cobra and Viper — command-first architecture, configuration management, environment variable binding, and in-memory CLI testing. Written by spf13, the original creator of both libraries.
aio-watermill-kit
Build event-driven Go apps with Watermill — Router, middleware, Pub/Sub, CQRS, and integrations for Kafka, AMQP, NATS, Redis Streams, and SQL.
go-hexagonal
Opinionated guide for building Go applications using a pragmatic layered architecture inspired by hexagonal principles.
go-backend
Um plugin para desenvolvimento de backends em Go, incluindo compilação, testes, verificação de estilo e Swagger, uma ferramenta para descrever APIs.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.