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/metalbear-co/skillsWrote 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/metalbear-co/skills/skills)<a href="https://agentmods.dev/plugins/metalbear-co/skills/skills"><img src="https://agentmods.dev/badge/plugins/metalbear-co/skills/skills/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/metalbear-co/skills/skills"><img src="https://agentmods.dev/badge/plugins/metalbear-co/skills/skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mirrord 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 9d 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": "mirrord",
"displayName": "mirrord",
"description": "Connect your agent to a live Kubernetes cluster with mirrord, so it tests code changes against real services. Covers setup, config, CI, database branching, queue splitting, and preview environments.",
"version": "1.1.1",
"author": {
"name": "MetalBear",
"email": "[email protected]",
"url": "https://metalbear.com"
},
"homepage": "https://metalbear.com/mirrord/ai/",
"documentationUrl": "https://metalbear.com/mirrord/docs",
"privacyPolicyUrl": "https://metalbear.com/legal/privacy-policy/",
"termsOfServiceUrl": "https://metalbear.com/legal/terms/",
"repository": "https://github.com/metalbear-co/skills",
"license": "MIT",
"keywords": ["mirrord", "kubernetes", "k8s", "metalbear", "dev-tools"],
"icon": "./.claude-plugin/icon.png"
}
What it installs
The manifest is a name and a version. 12 skills travel with it, and installing the plugin installs all of them — 1,598 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill mirrord-db-branching A 95 tokens
- Skill mirrord-prev-env A 122 tokens
- Skill mirrord-kafka A 189 tokens
- Skill mirrord-operator A 124 tokens
- Skill mirrord-up A 73 tokens
- Skill mirrord-temporal A 152 tokens
- Skill mirrord-quickstart A 89 tokens
- Skill mirrord-config A 73 tokens
- Skill mirrord-header-propagation A 237 tokens
- Skill mirrord-propagation-discovery A 273 tokens
- Skill mirrord-chaos A 119 tokens
- Skill mirrord-ci C 52 tokens
What ships with it
2 files beside plugin.json 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.
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.
- 9d ago Changed · +3 lines a6f6cefbdd3e
- 18d ago Changed · +2 lines b6bda4514771
- 1mo ago First seen · 15 lines scan A e17badd3fa6d
mirrord is a plugin published in the GitHub repository metalbear-co/skills (29 stars, last pushed 5d 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 2026-08-30.
Other plugins, from other repositories
database-cloud-optimization
Database query optimization, cloud cost optimization, and scalability improvements.
cloudflare-d1
Cloudflare D1 serverless SQLite on edge. Use for databases, migrations, bindings, or encountering D1ERROR, statement too long, too many requests queued errors.
cloudflare-kv
Cloudflare Workers KV global key-value storage. Use for namespaces, caching, TTL, or encountering KVERROR, 429 rate limits, consistency issues.
formae
MCP server and skills for formae infrastructure-as-code: manage cloud resources, handle drift, discover infrastructure, and build plugins.
deployment-strategies
Deployment patterns, rollback automation, and infrastructure templates.
multi-cursor
Official Cursor SDK coding harness.