reliability-review

reliability-review is a command for Claude Code from RoboFinSystems/robosystems. It costs 16 tokens per session (1,386 once invoked), scanned A, original, Apache-2.0.

A read-only review command for AWS reliability and resilience, meaning how well cloud systems continue working and recover from failures. It also produces evidence for the Availability area of SOC 2, a security and service-controls audit framework.

In plain words
What is it for?
Use it to inspect AWS resources and create a reliability report plus a prioritized improvement plan. The review is limited to read operations and must keep its sensitive output private.
Why use it?
It finds single points of failure, backup gaps, and recovery risks without changing the AWS account. It also organizes relevant findings for availability compliance work.

Command for Claude Code

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 commands/robofinsystems/robosystems/reliability-review
Clone the repo
git clone --depth 1 https://github.com/RoboFinSystems/robosystems

Made for: Claude Code.

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 reliability-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/robofinsystems/robosystems/reliability-review.svg)](https://agentmods.dev/commands/robofinsystems/robosystems/reliability-review)
Your own site
<a href="https://agentmods.dev/commands/robofinsystems/robosystems/reliability-review"><img src="https://agentmods.dev/badge/commands/robofinsystems/robosystems/reliability-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,386 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 $0.00016 $0.01386
Opus 5 $0.00008 $0.00693
Sonnet 5 $0.00003 $0.00277
Haiku 4.5 $0.00002 $0.00139

Measured 4d ago against content hash 4dc39439f474, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reliability-review 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.

.claude/commands/reliability-review.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run a read-only AWS reliability & resilience review (the Well-Architected Reliability pillar), then produce a report and a prioritized plan. Doubles as SOC 2 Availability (A1) evidence. Pairs with the reliability-review runbook (local/RoboSystems/runbooks/) for the account-specific detail — read it alongside this file, since it holds the live record of what's been accepted, deferred, or already remediated.

Scope & guardrails

  • Read-only. describe-* / list-* / get-* only; never get-secret-value. Any change (enabling Multi-AZ, standing up a backup plan, adjusting scaling) needs explicit user confirmation; CloudFormation/destructive actions are the user's to run.
  • Output is sensitive — never commit it. A reliability report names your single points of failure, backup gaps, and unrecoverable paths — a roadmap for both attackers and adversarial due-diligence. Vault or private Artifact only.
  • Feeds SOC 2 Availability. Tag findings that map to CC7.5 / A1 (backups, recovery, capacity) so this doubles as readiness evidence for /soc2-review.

Phase 1 — Redundancy & single points of failure

aws rds describe-db-instances --region us-east-1 --query 'DBInstances[].{id:DBInstanceIdentifier,multiAZ:MultiAZ,az:AvailabilityZone}'
aws elasticache describe-replication-groups --region us-east-1 --query 'ReplicationGroups[].{id:ReplicationGroupId,multiAZ:MultiAZ,automaticFailover:AutomaticFailover}'
aws autoscaling describe-auto-scaling-groups --region us-east-1 --query 'AutoScalingGroups[].{name:AutoScalingGroupName,min:MinSize,desired:DesiredCapacity,azs:AvailabilityZones}'

Then the surfaces the three calls above miss — each is its own SPOF class:

# Container services: desired vs running, per cluster
aws ecs list-clusters --region us-east-1
aws ecs describe-services --cluster <c> --services <s> --region us-east-1 \
  --query 'services[].{name:serviceName,desired:desiredCount,running:runningCount}'

# Managed search: node count, zone awareness, dedicated master, standby
aws opensearch list-domain-names --region us-east-1
aws opensearch describe-domain --domain-name <d> --region us-east-1 --query 'DomainStatus.ClusterConfig'

# Registries backing graph routing
aws dynamodb list-tables --region us-east-1

# Edge: distributions fronting the customer-facing apps
aws cloudfront list-distributions --query 'DistributionList.Items[].{id:Id,enabled:Enabled,aliases:Aliases.Items}'

# Functions on critical paths (secret rotation, volume management)
aws lambda list-functions --region us-east-1 --query 'Functions[].FunctionName'

Read the full file on GitHub · 77 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 · 77 lines · 16 tokens per session scan A 4dc39439f474

Subscribe to this mod's changes

reliability-review is a command published in the GitHub repository RoboFinSystems/robosystems (24 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 1,386 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.