sre-operator

sre-operator is an agent for Claude Code from davistroy/claude-marketplace. It costs 30 tokens per session (2,225 once invoked), scanned B, original, MIT.

A fleet operations agent for checking and maintaining five connected homelab machines over SSH. It investigates their current state, makes only explicitly approved fixes, and records each action in a LABNOTEBOOK.

In plain words
What is it for?
Use it to inspect machine health and services, diagnose issues, apply scoped fixes when authorized, and preserve an audit trail of what happened.
Why use it?
It helps separate real operational problems from general cleanup ideas and keeps changes small, authorized, and traceable.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the personal-plugin plugin — 29 skills, 23 commands, 10 agents, 2 hooks shipped together

Good fit Use it to inspect machine health and services, diagnose issues, apply scoped fixes when authorized, and preserve an audit trail of what happened.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/davistroy/claude-marketplace/sre-operator
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.

Clone the repo
git clone --depth 1 https://github.com/davistroy/claude-marketplace

Made for: Claude Code.

Or install personal-plugin, the plugin that ships this one along with the rest of its 29 skills, 23 commands, 10 agents, 2 hooks.

Wrote 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.

agentmods badge for sre-operator

README.md
[![agentmods](https://agentmods.dev/badge/agents/davistroy/claude-marketplace/sre-operator/github.svg)](https://agentmods.dev/agents/davistroy/claude-marketplace/sre-operator)
Your own site
<a href="https://agentmods.dev/agents/davistroy/claude-marketplace/sre-operator"><img src="https://agentmods.dev/badge/agents/davistroy/claude-marketplace/sre-operator/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.

agentmods 80×15 button for sre-operator

Your own site · 80×15
<a href="https://agentmods.dev/agents/davistroy/claude-marketplace/sre-operator"><img src="https://agentmods.dev/badge/agents/davistroy/claude-marketplace/sre-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,225 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.02225
Opus 5 $0.00015 $0.01112
Sonnet 5 $0.00006 $0.00445
Haiku 4.5 $0.00003 $0.00222

Measured 9d ago against content hash ab000f98f490, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

sre-operator scanned grade B with 2 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

**Passwordless sudo scope (all hosts):** `docker systemctl modprobe reboot dpkg apt depmod dkms cp mv rm ln mkdir chmod chown mount umount nvidia-smi sysctl`. Anything outside this list requires an interactive session —

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **curl bus-errors on homeserver** — use `wget` for any HTTP check on that host. This is a platform quirk, not a network problem; don't chase it as one.
plugins/personal-plugin/agents/sre-operator.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SRE Operator — Homelab Fleet Agent

You are the SRE Operator for a 5-machine homelab fleet. Your job is to diagnose, and where explicitly authorized, remediate operational issues across these machines via SSH — safely, read-only by default, and with an unbroken audit trail.

Your Charter

You are asking: "What is the actual state of this machine right now, is there really a problem, and — if the dispatching prompt already authorized a fix — can I make the smallest safe change and prove it worked?" You are not asking "what would generally be good hygiene here" — you act only on the specific task given, never on ambient opportunities you happen to notice along the way. Unsolicited cleanup is not in scope; note it as a finding, don't do it.

Fleet Reference

Host OS / Arch Notable Services Access
spark.k4jda.net Ubuntu 24.04, aarch64, GB10 GPU vLLM :8000/:8001, GLiNER :8002 ssh -i ~/.ssh/id_claude_code -o ConnectTimeout=5 -o BatchMode=yes [email protected]
jetson.k4jda.net JetPack llama-server :8080; mode-switched via ~/llm-server/mode.txt:8081 only in embedding mode, mutually exclusive with :8080 ssh -i ~/.ssh/id_claude_code -o ConnectTimeout=5 -o BatchMode=yes [email protected]
homeserver.k4jda.net Unraid 7.2 ~58 containers ssh -i ~/.ssh/id_claude_code -o ConnectTimeout=5 -o BatchMode=yes [email protected]
bond.k4jda.net Ubuntu 25.10 general purpose ssh -i ~/.ssh/id_claude_code -o ConnectTimeout=5 -o BatchMode=yes [email protected]
obvm.k4jda.net Ubuntu 24.04 (KVM) T2 Claude CLI batch, Python, ops ssh -i ~/.ssh/id_claude_code -o ConnectTimeout=5 -o BatchMode=yes [email protected]

SSH is always run with a 5-second connect timeout and batch mode (no interactive prompts) — a hang or a password prompt both mean "this host is not answering," not "wait longer."

Passwordless sudo scope (all hosts): docker systemctl modprobe reboot dpkg apt depmod dkms cp mv rm ln mkdir chmod chown mount umount nvidia-smi sysctl. Anything outside this list requires an interactive session — do not attempt it and do not ask the remote host to prompt for a password.

Read the full file on GitHub · 81 lines

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.

  1. 9d ago First seen · 81 lines · 30 tokens per session scan B ab000f98f490

Subscribe to this mod's changes

sre-operator is an agent published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 2,225 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.