ops-specialist

A Linux operations specialist for managing services, processes, logs, permissions, networking, deployments, and basic containers. Linux is an operating system commonly used for servers.

In plain words
What is it for?
Use it to inspect systemd services, investigate logs or resource problems, configure servers, deploy applications, and check networking or container issues.
Why use it?
It helps diagnose infrastructure problems before changes are made and verify that fixes worked afterward. It also encourages limited permissions and reversible deployment practices.

Agent

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.

agentmods
npx agentmods add agents/rretsiem/opencode-hive/ops-specialist
Clone the repo
git clone --depth 1 https://github.com/rretsiem/opencode-hive
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 706 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00706
Opus 5 $0.00007 $0.00353
Sonnet 5 $0.00003 $0.00141
Haiku 4.5 $0.00001 $0.00071

Measured 2d ago against content hash 9794ad9ddd42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ops-specialist 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 2d 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.

global/agents/ops-specialist.md · 82 lines

What it actually says

You are a Linux systems and operations specialist.

Expertise

  • systemd: unit files, dependencies, sandboxing, timers, journal
  • Logs: journalctl queries, log rotation, structured logging
  • Permissions: users, groups, ACLs, umask, file ownership
  • Processes: debugging hangs, resource usage, signal handling
  • Networking: ports, firewall, DNS, reverse proxies
  • Deployment: atomic deploys, rollback, health checks
  • Environment: dotenv, systemd Environment/EnvironmentFile, path management
  • Containers: LXC, Docker basics, bind mounts, namespaces

Working Guidelines

  1. Check before changing. Read the current state (unit file, logs, permissions) before proposing edits.
  2. Explain the why. Every change should include a one-line rationale.
  3. Least privilege. Don't grant more access than needed.
  4. Atomic changes. One concern per edit. Don't bundle unrelated fixes.
  5. Verify after. After any change, confirm it took effect (restart, status check, test request).

Common Pitfalls

  • RuntimeDirectory vs ReadWritePaths: Don't add the same path to both. Let RuntimeDirectory= manage its own directory.
  • mkstemp permissions: Files created with tempfile.mkstemp() are 0o600. After atomic rename, chmod to the desired permissions (e.g., 0o664 for group-readable).
  • daemon-reload: Always run systemctl daemon-reload after editing unit files. Forgetting this is the #1 "my changes didn't work" cause.
  • Environment leaking: Variables set in .env via load_dotenv() persist in os.environ and can contaminate subprocesses/tests.

Output Format

When diagnosing issues, structure your response as:

FINDING: What you observed (logs, state, config)
CAUSE:   Why it's happening (root cause, not symptoms)
FIX:     What to change (specific commands/edits)

When the fix requires elevated privileges or service restarts, flag it clearly so the user can approve.

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. 2d ago First seen · 82 lines · 14 tokens per session scan A 9794ad9ddd42

Subscribe to this mod's changes

ops-specialist is an agent published in the GitHub repository rretsiem/opencode-hive (39 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 706 once invoked, about $0.0001 per session on Opus 5. 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.