A server-operations plugin that lets a coding agent manage remote machines over SSH without exposing passwords, keys, host details, or ports to the agent.

Use it for health checks, Docker and system-service control, log viewing, configuration edits, read-only PostgreSQL inspection, and declarative deployments.

It reduces the need to hand sensitive connection credentials to an automated tool while still supporting common server tasks.

sshepherd — Plugin by Antheurus

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.

Claude Code

/plugin marketplace add Antheurus/sshepherd

agentmods

npx agentmods add plugins/antheurus/sshepherd/marketplace

Clone the repo

git clone --depth 1 https://github.com/Antheurus/sshepherd

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

sshepherd 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 yesterday.

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.

.claude-plugin/marketplace.json · 31 lines

What it actually says

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "sshepherd",
  "description": "Zero-knowledge SSH server operations for Claude Code — health checks, docker/systemd control, log tailing, config edits, read-only Postgres introspection, and declarative deploys, without the agent ever seeing a credential.",
  "owner": {
    "name": "Antheurus"
  },
  "plugins": [
    {
      "name": "sshepherd",
      "source": "./",
      "description": "Server operations over SSH — health checks, container/service control, log tailing, config edits, Postgres introspection, and declarative deploys — driven through a single compiled CLI that never lets the agent see a password, private key, host, user, or port.",
      "version": "0.1.0",
      "author": {
        "name": "Antheurus"
      },
      "license": "MIT",
      "keywords": [
        "ssh",
        "devops",
        "cli",
        "security",
        "zero-knowledge",
        "postgres",
        "deploy"
      ],
      "category": "development"
    }
  ]
}

Files

What ships with it

1 file beside marketplace.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.

plugin.json 661 B

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.

yesterday First seen · 31 lines scan A 1ac1bd0e677d

Subscribe to this mod's changes

sshepherd is a plugin published in the GitHub repository Antheurus/sshepherd (0 stars, last pushed 1mo 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.

Databases DevOps and cloud agent-skills claude-code claude-code-skills claude-skills cli deploy

defang

Deploy Docker Compose apps to your own cloud account using Defang. Includes a /defang:deploy skill and Defang MCP server integration.

DefangLabs/defang · not measured

sound

Code taste as installable rules. Probe a repo's stack, select only the rules its code shows a surface for (evidence-cited per rule), confirm, and scaffold a browsable .claude/sound/ rule map (surfaced by the sound:prime skill). Installed rules are user-owned; re-runs reconcile.

saadshahd/moo.md · not measured

sshepherd