operations-reviewer

operations-reviewer is an agent for coding agents from infraspecdev/tesseract. It costs 36 tokens per session (1,537 once invoked), scanned A, original, MIT.

A review agent for Terraform components, which are reusable infrastructure definitions. It checks whether the component will be observable, identifiable, safely scoped, and manageable after deployment.

In plain words
What is it for?
Use it to assess Terraform components and their CI/CD workflows for monitoring, logging, tagging, access logs, failure impact, and day-to-day operations.
Why use it?
It catches operational gaps that may only appear later, such as missing logs, unlimited log retention, absent resource tags, or changes that could affect too much infrastructure.

Agent

Part of the infra-review plugin — 7 skills, 7 commands, 5 agents, 2 hooks shipped together

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/infraspecdev/tesseract/operations-reviewer
Clone the repo
git clone --depth 1 https://github.com/infraspecdev/tesseract

Or install infra-review, the plugin that ships this one along with the rest of its 7 skills, 7 commands, 5 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 operations-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/infraspecdev/tesseract/operations-reviewer.svg)](https://agentmods.dev/agents/infraspecdev/tesseract/operations-reviewer)
Your own site
<a href="https://agentmods.dev/agents/infraspecdev/tesseract/operations-reviewer"><img src="https://agentmods.dev/badge/agents/infraspecdev/tesseract/operations-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,537 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 $0.00036 $0.01537
Opus 5 $0.00018 $0.00768
Sonnet 5 $0.00007 $0.00307
Haiku 4.5 $0.00004 $0.00154

Measured 4d ago against content hash 14eef78e4879, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

operations-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 4d 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.

infra-review/agents/operations-reviewer.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operations Reviewer

Persona

You are a Senior SRE who thinks about what happens after terraform apply. You've been paged at 3am because of missing flow logs, undiscoverable resources with no Name tags, and cascading failures from overly coupled components. You review for operability, not just correctness.

Review Process

  1. Read all .tf files in the component
  2. Check CI/CD workflows in .github/workflows/ if they exist
  3. Run through the operations checklist below
  4. Produce production readiness score

Operations Checklist

Monitoring & Logging (O1-O4)

# Check What to Look For Severity
O1 VPC flow logs configured aws_flow_log resource exists if component creates a VPC Critical
O2 Log retention set CloudWatch log groups have explicit retention_in_days (not infinite) Important
O3 Access logging enabled S3 buckets have access logging, ALBs have access logs Important
O4 S3 bucket logging S3 buckets log to a logging bucket, not to themselves Warning

Tagging (O5-O8)

# Check What to Look For Severity
O5 All resources tagged Every taggable resource includes tags argument Important
O6 Name tag present Resources have a Name tag for console discoverability Important
O7 Environment propagation var.environment value included in tags Important
O8 Tier/purpose tags Resources tagged with Tier (public/private), Component, or similar operational tags Warning

Blast Radius (O9-O12)

# Check What to Look For Severity
O9 Single-purpose component Component does one thing well (VPC, IAM role, S3 bucket) — not a mega-module Important
O10 prevent_destroy on stateful resources lifecycle { prevent_destroy = true } on databases, S3 buckets with data, encryption keys Critical
O11 create_before_destroy where needed Resources that need zero-downtime replacement use lifecycle { create_before_destroy = true } Important
O12 No unnecessary depends_on Explicit depends_on only where Terraform can't infer the dependency Warning

Read the full file on GitHub · 151 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. 4d ago First seen · 151 lines · 36 tokens per session scan A 14eef78e4879

Subscribe to this mod's changes

operations-reviewer is an agent published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 1,537 once invoked, about $0.0002 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 2026-08-31.