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.
/plugin marketplace add VoltAgent/awesome-claude-code-subagentsnpx agentmods add plugins/voltagent/awesome-claude-code-subagents/02-language-specialistsgit clone --depth 1 https://github.com/VoltAgent/awesome-claude-code-subagentsGrade A, and why
voltagent-lang 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- voltagent-lang — 100% identical, 0 lines differ
- voltagent-lang — 97% identical, 3 lines differ
What it actually says
{
"name": "voltagent-lang",
"version": "1.0.4",
"description": "Language-specific expert agents with deep framework knowledge - Python, TypeScript, Go, Rust, Java, and more",
"author": {
"name": "VoltAgent Community",
"url": "https://github.com/VoltAgent"
},
"repository": "https://github.com/VoltAgent/awesome-claude-code-subagents",
"license": "MIT",
"agents": [
"./angular-architect.md",
"./cpp-pro.md",
"./csharp-developer.md",
"./django-developer.md",
"./dotnet-core-expert.md",
"./dotnet-framework-4.8-expert.md",
"./elixir-expert.md",
"./expo-react-native-expert.md",
"./fastapi-developer.md",
"./flutter-expert.md",
"./golang-pro.md",
"./java-architect.md",
"./javascript-pro.md",
"./kotlin-specialist.md",
"./laravel-specialist.md",
"./nextjs-developer.md",
"./node-specialist.md",
"./php-pro.md",
"./powershell-5.1-expert.md",
"./powershell-7-expert.md",
"./python-pro.md",
"./rails-expert.md",
"./react-specialist.md",
"./rust-engineer.md",
"./spring-boot-engineer.md",
"./sql-pro.md",
"./swift-expert.md",
"./symfony-specialist.md",
"./typescript-pro.md",
"./vue-expert.md"
]
}
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 · 44 lines scan A 9b03f2c52379
voltagent-lang is a plugin published in the GitHub repository VoltAgent/awesome-claude-code-subagents (24,790 stars, last pushed yesterday), 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 2026-08-30.
Other plugins, from other repositories
dotnet-coverage-kit
Characterization-test backfill and spec-test enforcement for .NET services. Deterministic C0/C1 measurement via dotnet-coverage, with a checked-in manifest that explains every inclusion and exclusion.
dual-boot
Sets up and manages dual-boot Ruby and Rails environments using the nextrails gem, based on FastRuby.io methodology.
cto-team-marketplace
Plugin marketplace listing 1 plugin: cto-team.
claude-cto-team
Strategic CTO advisory team with specialized agents for architecture design, plan validation, and technology decisions.
swiftwasm-skills
Agent Skills for SwiftWasm ecosystem - JavaScriptKit, BridgeJS, and Wasm porting guidance.
go-ultimate
Opinionated Go development skill — architecture, conventions, production readiness, repo/CI hygiene, review, and MCP/agent patterns.