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/LerianStudio/ringWrote 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/lerianstudio/ring/dev-team)<a href="https://agentmods.dev/plugins/lerianstudio/ring/dev-team"><img src="https://agentmods.dev/badge/plugins/lerianstudio/ring/dev-team/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/lerianstudio/ring/dev-team"><img src="https://agentmods.dev/badge/plugins/lerianstudio/ring/dev-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ring-dev-team 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 1mo 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": "ring-dev-team",
"displayName": "Ring Dev Team",
"description": "24 specialized developer agents + 35 development skills. Backend (Go/TypeScript) and frontend (React/Next.js) dev cycles, DevOps, QA, SRE, and the parallel code-review pool.",
"version": "2.3.0",
"author": {
"name": "Lerian Studio",
"email": "[email protected]"
},
"homepage": "https://github.com/lerianstudio/ring/tree/main/dev-team",
"repository": "https://github.com/lerianstudio/ring",
"license": "MIT",
"keywords": [
"agents",
"developers",
"golang",
"backend",
"devops",
"frontend",
"react",
"nextjs",
"qa",
"testing",
"accessibility",
"e2e",
"playwright",
"performance",
"sre",
"reliability",
"infrastructure",
"refactoring",
"simplify",
"multi-tenant",
"lib-commons",
"code-review"
],
"skills": "./skills/",
"agents": "./agents/",
"hooks": "./hooks/hooks.json"
}
What it installs
The manifest is a name and a version. 35 skills, 24 agents travel with it, and installing the plugin installs all of them — 4,597 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ring:migrating-to-lib-observability A 104 tokens
- Skill ring:using-lib-streaming A 99 tokens
- Skill ring:using-lib-systemplane A 106 tokens
- Skill ring:applying-composition-patterns A 68 tokens
- Skill ring:using-lib-observability A 102 tokens
- Skill ring:using-outbox A 98 tokens
- Skill ring:adopting-lib-commons-huma-wrapper A 142 tokens
- Skill ring:using-tracing A 94 tokens
- Skill ring:reviewing-operational-risk A 123 tokens
- Skill ring:running-dev-cycle A 122 tokens
- Skill ring:mapping-service-resources A 97 tokens
- Skill ring:migrating-to-lib-systemplane A 113 tokens
- Skill ring:using-lib-commons A 98 tokens
- Skill ring:implementing-readyz A 101 tokens
- Skill ring:instrumenting-streaming-events A 102 tokens
- Skill ring:planning-codebase-simplification A 105 tokens
- Skill ring:using-assert A 99 tokens
- Skill ring:using-runtime A 91 tokens
- Skill ring:adding-multi-tenancy A 95 tokens
- Skill ring:implementing-tasks A 103 tokens
- Skill ring:managing-dev-cycle A 85 tokens
- Skill ring:applying-licenses A 94 tokens
- Skill ring:auditing-dependency-security A 102 tokens
- Skill ring:detecting-goroutine-leaks A 109 tokens
- Skill ring:generating-llms-txt A 109 tokens
- Skill ring:hardening-dockerfiles A 106 tokens
- Skill ring:planning-backend-refactor A 93 tokens
- Skill ring:using-dev-team A 82 tokens
- Skill ring:verifying-code A 101 tokens
- Skill ring:checking-frontend-quality A 102 tokens
- Skill ring:validating-acceptance-criteria A 100 tokens
- Skill ring:writing-dev-reports A 87 tokens
- Skill ring:creating-helm-charts B 92 tokens
- Skill ring:running-dev-cycle-frontend C 114 tokens
- Skill ring:planning-frontend-refactor C 100 tokens
- Agent ring:backend-go A 34 tokens
- Agent ring:backend-ts A 43 tokens
- Agent ring:commons-reviewer A 63 tokens
- Agent ring:dead-code-reviewer A 62 tokens
- Agent ring:nil-reviewer A 59 tokens
- Agent ring:perf-reviewer A 62 tokens
- Agent ring:security-reviewer A 33 tokens
- Agent ring:tenancy-reviewer A 40 tokens
- Agent ring:bff-ts A 47 tokens
- Agent ring:code-reviewer A 37 tokens
- Agent ring:devops A 29 tokens
- Agent ring:logic-reviewer A 42 tokens
- Agent ring:prompt-reviewer A 32 tokens
- Agent ring:qa A 52 tokens
- Agent ring:sre A 39 tokens
- Agent ring:systemplane-reviewer A 40 tokens
- Agent ring:test-reviewer A 39 tokens
- Agent ring:ui-designer A 42 tokens
- Agent ring:ui-engineer A 46 tokens
- Agent ring:obs-reviewer A 39 tokens
- Agent ring:qa-frontend A 53 tokens
- Agent ring:streaming-reviewer A 38 tokens
- Agent ring:helm B 38 tokens
- Agent ring:frontend C 50 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.
- 1mo ago First seen · 41 lines scan A ec1fe472c043
ring-dev-team is a plugin published in the GitHub repository LerianStudio/ring (217 stars, last pushed 2d ago), licensed Apache-2.0. 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 2026-09-15.
Other plugins, from other repositories
roam-code
Local codebase intelligence + change-safety gates for coding agents. REQUIRES Python 3.10+ and pip install roam-code first — this plugin launches the roam binary from your PATH, and its MCP server cannot start without it. Pre-indexes your repo's symbols, call graph, deps, and git history into SQLite (28 languages.
claude-playbook
Engineering guardrails for Claude Code: path-scoped rules, review and verification skills, specialist subagents, and hooks that enforce what instructions only request.
dotnet-backend
Pure .NET 10 backend architecture for Kestrel-hosted REST and SignalR services with DI, data access, and SOLID review.
nextjs
Minimal core plus frontend feature building, UI design, code review, repo audit, debugging, and test writing.
backend-architecture
Small, opinionated architecture guide for production backend services across languages and frameworks.
backend-validator
Backend API and WebSocket validation via Hurl, websocat, and oauth2c with OIDC token caching.