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.
npx agentmods add commands/robofinsystems/robosystems/reliability-reviewgit clone --depth 1 https://github.com/RoboFinSystems/robosystemsWrote 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.
[](https://agentmods.dev/commands/robofinsystems/robosystems/reliability-review)<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>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.
| Model | Per session | Once 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 |
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.
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; neverget-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'
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.
- 4d ago First seen · 77 lines · 16 tokens per session scan A 4dc39439f474
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.
Other commands, from other repositories
fill-event-triage
체결(fill) 이벤트, 특히 매도 체결 후 현금 재배치 판단을 read-only 트리아지로 자동 기동해 dry-run 제안을 남긴다. ROB-755.
crypto-alert-triage
Command "crypto-alert-triage" from mgh3326/auto_trader, covering crypto-alert-triage, 입력, 1. 맥락 복원 (반드시 이 순서), 2. 분석 and 3. dryrun 미리보기 (read-only).
akb-production-review
Review AKB production-governance docs and hooks.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.