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 makifbaysal/tasktrooper --skill cloud-deploy-gcp-awsgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/cloud-deploy-gcp-aws)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/cloud-deploy-gcp-aws"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/cloud-deploy-gcp-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/makifbaysal/tasktrooper/cloud-deploy-gcp-aws"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/cloud-deploy-gcp-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 | $0.00054 | $0.01101 |
| Opus 5.5 | $0.00022 | $0.00440 |
| Sonnet 5.5 | $0.00011 | $0.00220 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
cloud-deploy-gcp-aws scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- End every deploy job with a smoke step: curl the health endpoint (Cloud Run revision URL / ECS service URL / ALB DNS) and **fail the job on non-200**. A failing smoke step fails the deploy — the release goes `failed` a How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Deploy — GCP & AWS (backend/worker)
Overview
A backend deploy ships the container the repo already builds, not a re-implementation. The same image runs on Google Cloud Run and on AWS ECS — the deploy workflow only differs in the auth handshake and the deploy command. Read [[ci-cd-pipeline-authoring]] first: it defines the workflow naming/dispatch contract this skill fills in with real cloud steps.
Core principle: One image, one health-checked deploy per environment, authenticated by OIDC — never a hand-rolled server or a committed key.
Pick the target, then copy the boilerplate
- Decide the cloud (project's existing infra wins) and app type (
backendorworker). search_boilerplate_catalog→deploy gcp backend,deploy aws worker, etc. Copy that folder'sdeploy-stage/preprod/prod.ymlinto the project's.github/workflows/as<id>-deploy-<env>.yml.- Fill in the repo/environment vars its README lists (project id, region, service name, image repo). Set up the OIDC trust once (WIF pool / IAM role) — the README has the exact steps.
GCP — Cloud Run
- Auth:
google-github-actions/authwithworkload_identity_provider+service_account(no key JSON). - Deploy:
gcloud run deploy $SERVICE --image $IMAGE --region $REGION(or--source .to build on deploy). Cloud Run gives you the revision URL to smoke-test. - Worker (no HTTP ingress): deploy as a Cloud Run job (
gcloud run jobs deploy ... && gcloud run jobs execute) or a GKE workload — not a public service.
AWS — ECS Express Mode / Fargate
- Auth:
aws-actions/configure-aws-credentialswithrole-to-assume(OIDC), no access keys. - ECS Express Mode is AWS's recommended default (App Runner stopped accepting new customers on 2026-04-30; existing App Runner services keep working, but don't build new ones there): push the image to ECR, then let Express Mode provision and run the service from it — the simplest path for a single service today.
- ECS Fargate (more control over task definitions, scaling, networking): push to ECR, render the task definition,
aws-actions/amazon-ecs-deploy-task-definitionwithwait-for-service-stability: true. - Worker: an ECS service with no load balancer / no public subnet.
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.
- 8d ago First seen · 58 lines · 54 tokens per session scan A 26798bf75977
cloud-deploy-gcp-aws is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 1,101 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.
Other skills, from other repositories
render
Use when deploying or fixing an app on Render — web services, background workers, cron jobs, private services, managed Postgres and Key-Value, and especially the render.yaml Blueprint. Covers deploys that fail with no open ports detected, 502s on first deploy, free-tier cold starts, and a free Postgres about to expire…
aiq-deploy
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
dynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.
mcore-run-on-slurm
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDADEVICEMAXCONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
dynamo-interconnect-check
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.