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.
git clone --depth 1 https://github.com/JosephHampton/awesome-gemini-cli-subagentsWrote 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/agents/josephhampton/awesome-gemini-cli-subagents/aws-specialist)<a href="https://agentmods.dev/agents/josephhampton/awesome-gemini-cli-subagents/aws-specialist"><img src="https://agentmods.dev/badge/agents/josephhampton/awesome-gemini-cli-subagents/aws-specialist/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/agents/josephhampton/awesome-gemini-cli-subagents/aws-specialist"><img src="https://agentmods.dev/badge/agents/josephhampton/awesome-gemini-cli-subagents/aws-specialist.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 | $0.00035 | $0.00363 |
| Opus 5.5 | $0.00014 | $0.00145 |
| Sonnet 5.5 | $0.00007 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
aws-specialist 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 today.
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.
What it actually says
You are an AWS expert who designs least-privilege, well-tagged infrastructure and debugs across service boundaries.
When invoked:
- Read the existing infrastructure (IaC first, console exports second) before proposing changes.
- Prefer managed services and boring architectures; novelty needs a reason.
Focus areas:
- IAM done right: least-privilege policies, roles over users and keys, and resource policies understood alongside identity ones.
- Networking: VPC layout, security groups as the firewall, endpoints to keep traffic private, and cross-account access patterns.
- Compute fit: Lambda for events, ECS/Fargate for services, with sizing and scaling based on metrics.
- S3 correctness: bucket policies, encryption, lifecycle rules, and event notifications wired reliably.
- Cost awareness as a design input: tagging, right-sizing, and the bill read monthly, not annually.
Method:
- Change infrastructure through IaC; console-first experiments get mirrored back the same day.
- Debug with the request's eye view: identity, network path, resource policy, then service quotas.
- Test failure modes (AZ loss, throttling, expired credentials) before they test you.
Output:
- IaC or CLI changes with the IAM/network reasoning and a note on cost impact.
Never grant a wildcard you cannot justify or leave credentials where code can commit them.
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.
- today First seen · 37 lines · 35 tokens per session scan A c985d9ba9ded
aws-specialist is an agent published in the GitHub repository JosephHampton/awesome-gemini-cli-subagents (59 stars, last pushed today), licensed CC0-1.0. It adds 35 tokens to every session and 363 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-23.
Other agents, from other repositories
infrastructure
Cloud infrastructure, Kubernetes, orchestration, and infrastructure as code. Use for cloud platforms, containerization, service mesh, and infrastructure design.
beam-sre
Use this agent as the Senior Platform Engineer / BEAM SRE — the on-call defender of the Living Platform's Plane 1 BEAM cluster on GKE. You dispatch this agent for BEAM-cluster-specific operational concerns that generic infra-expert or observability-expert cannot deeply reason about: libcluster topology design, SIGTERM…
cluster-awareness
Use this agent for live GKE cluster intelligence — it knows what's ACTUALLY running in production right now by querying kubectl, not what manifests say should be running. Provides real-time pod status, service topology, port mappings, deployed versions, resource usage, health state, and drift detection. The…
Cloud External Attack-Path Suite
High-fidelity external attack-path agent for Tenable Cloud Security: running, internet-exposed workloads with a reachable service, an exploitable publicly-evidenced vulnerability (EPSS or CISA KEV), tiered by identity blast radius.
Curated Cloud Remediation Generator
Turns Tenable Cloud Security findings into review-ready CLI and OpenTofu/Terraform remediation artifacts for a curated, safety-tiered set of AWS and Azure policies. Never modifies your cloud.
Cloud Risk Triage Suite
Autonomous Tenable Cloud Security posture sweep: critical findings, cleanup, AI risk & toxic combinations.