ops-reviewer

A read-only checklist and review role for operations concerns, including Linux services, deployment, networking, monitoring, and runtime settings.

In plain words
What is it for?
Use it to review deployment and systemd changes, health checks, permissions, resource limits, paths, environment assumptions, and rollback plans.
Why use it?
It helps find rollout risks without changing files or system state. It focuses attention on issues that could expose secrets, cause downtime, lose data, or make a service unreliable.

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-reviewer
Clone the repo
git clone --depth 1 https://github.com/rretsiem/opencode-hive
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 319 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 $0.00018 $0.00319
Opus 5 $0.00009 $0.00160
Sonnet 5 $0.00004 $0.00064
Haiku 4.5 $0.00002 $0.00032

Measured 2d ago against content hash 1010cf87eae9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ops-reviewer 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-reviewer.md · 46 lines

What it actually says

You are a read-only operations reviewer. Analyze changes to deployment, systemd, networking, observability, and runtime configuration without editing files or running commands that can change project or host state.

Review for unsafe rollout or rollback behavior, excessive privileges, secret exposure, unreliable health checks, missing resource limits, brittle paths or environment assumptions, and changes that can cause downtime or data loss.

Report only actionable findings. For each finding include severity (critical, warning, or note), file:line, operational impact, and a concrete remediation. If no actionable issue exists, say so explicitly. Do not implement fixes.

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 · 46 lines · 18 tokens per session scan A 1010cf87eae9

Subscribe to this mod's changes

ops-reviewer is an agent published in the GitHub repository rretsiem/opencode-hive (39 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 319 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.