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 skills add SumonMSelim/agentguard --skill awsgit clone --depth 1 https://github.com/SumonMSelim/agentguardWrote 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/skills/sumonmselim/agentguard/aws)<a href="https://agentmods.dev/skills/sumonmselim/agentguard/aws"><img src="https://agentmods.dev/badge/skills/sumonmselim/agentguard/aws/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sumonmselim/agentguard/aws"><img src="https://agentmods.dev/badge/skills/sumonmselim/agentguard/aws.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00947 |
| Opus 5.5 | $0.00000 | $0.00379 |
| Sonnet 5.5 | $0.00000 | $0.00189 |
| Haiku 4.5 | $0.00000 | $0.00095 |
Grade A, and why
aws 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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AWS
Account structure
- Separate AWS accounts per environment (dev, staging, prod). Never share prod account
- AWS Organizations with SCPs for org-wide guardrails. Control Tower for multi-account setup
- Dedicated logging/security account. Ship CloudTrail, Config, and GuardDuty findings there
- SCPs: deny root usage, deny disabling CloudTrail/GuardDuty, enforce region restrictions
IAM
- Least privilege. No wildcard actions/resources (
*) in production - No long-lived human access keys. Use IAM Identity Center, roles, temp credentials
- EC2/Lambda/ECS: instance profiles and execution roles. Never credentials in code or env vars
- EKS: IRSA (IAM Roles for Service Accounts) per pod. No node-level roles for app permissions
- Separate roles per service and environment. No shared roles across workloads
- Permission boundaries for delegated admin. Prevents privilege escalation via role creation
- MFA on all IAM users. Root locked — never used
- Rotate credentials. Audit via IAM Access Analyzer. Remove unused permissions
Secrets
- Store in Secrets Manager or SSM Parameter Store (SecureString). Never in env vars, AMIs, images, Terraform state, or CloudFormation parameters (use SSM/Secrets Manager references)
- Auto-rotate via Secrets Manager rotation lambdas
- Reference by ARN in task definitions and Lambda config. Never pass values directly
Networking
- VPC per environment. Public subnets: load balancers only. Private: compute and data
- Security groups: ingress from known sources only. No
0.0.0.0/0except ALB port 443 - WAF in front of ALB and CloudFront for all public-facing workloads
- No EC2 public IPs unless required. Session Manager for all access — no SSH
- NACLs as secondary subnet-level layer
- VPC Flow Logs enabled. Ship to CloudWatch or S3
- PrivateLink for AWS service access where internet routing is avoidable
Security
- CloudTrail in all regions. Logs to dedicated locked-down S3 bucket
- GuardDuty enabled. Security Hub enabled with baseline standard (AWS Foundational or CIS)
- Macie enabled on S3 buckets containing sensitive or PII data
- S3: block public access at account level. Explicit bucket policies only
- S3 versioning + MFA delete on sensitive buckets
- S3 lifecycle policies: transition to IA/Glacier, expire old versions. Unbounded storage compounds cost
- KMS: customer-managed keys (CMK) for sensitive data at rest. Audit key usage
- Config enabled with conformance packs for drift detection
- ECR: image scanning on push. Block deploy on critical/high CVEs
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.
- 1mo ago First seen · 74 lines · 0 tokens per session scan A 3ee1a1c1be03
aws is a skill published in the GitHub repository SumonMSelim/agentguard (54 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 947 tokens. 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 skills, from other repositories
tcapi
A helper for managing Tencent Cloud resources through Tencent Cloud's command-line API tool. Tencent Cloud is a cloud-services provider offering products such as virtual servers, storage, networks, and containers.
nettools
A collection of network and domain lookup tools for checking reachability, registration details, DNS records, and domain prices. DNS is the system that maps names such as example.com to services, while RDAP provides domain registration information.
metago-sre-engineer
SRE Engineer - specializes in high availability, backup, disaster recovery, chaos engineering, SLO definition, and runbook generation.
metago-deploy-engineer
Deployment Engineer - specializes in private/cloud/edge deployments, Helm charts, canary releases, and rollback.
metago-ops-engineer
Operations Engineer - specializes in DNS, SSL, reverse proxy, production environment, and CI/CD pipeline configuration.
insforge-cli
A command-line tool for creating and managing InsForge backends and their cloud setup. InsForge is a backend service for applications.