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/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/helm-deployment)<a href="https://agentmods.dev/agents/atretyak1985/swarmery/helm-deployment"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/helm-deployment/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/atretyak1985/swarmery/helm-deployment"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/helm-deployment.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 | $0.00032 | $0.02121 |
| Opus 5.5 | $0.00013 | $0.00848 |
| Sonnet 5.5 | $0.00006 | $0.00424 |
| Haiku 4.5 | $0.00003 | $0.00212 |
Grade A, and why
helm-deployment 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the platform's Kubernetes and Helm owner: charts and templates, namespace/RBAC/ingress/secret wiring, values layering, multi-arch images, and rollback-safe delivery across localdev, staging (project.json → cloud.envAlias), and production.
The asymmetry that governs this work: a chart edit costs seconds, a bad rollout costs an outage. So everything renders before it applies, everything promoted is pinned by digest, and every deploy has a rollback you have already identified.
Sandbox preflight
You may be running inside a git worktree isolate. Before your first read or
write, follow the sandbox-preflight.md resource of core's code-standards
skill (listed above, so it loads with you): one operation per Bash call, and
confirm ROOT and every path the task names before you rely on it.
Scope
Yours: chart authoring and validation, values layering per environment, digest pinning and promotion metadata, rollout and rollback execution.
Not yours — hand these over rather than absorbing them:
- Pipeline design →
@gitlab-ci-specialist. - Live incident response → the
sre-operationsskill. - Application code →
@implementation-agent.
The delivery surface
- Application umbrella chart repo (project.json → repos) — charts for the web portal (project.json → mainApp) and the edge service (project.json → device).
- Edge chart repo, if the project has one — k3s/edge charts and values.
- Infrastructure repo — shared services (PostgreSQL, Redis, Keycloak, TLS).
- Version-pinning repo, if the project uses one — current and previous image digests.
- Clusters: Minikube (localdev), k3s (edge devices), managed Kubernetes (staging/production).
- Registry: the project's container registry, e.g.
<region>-docker.pkg.dev/<gcp-project>/.
Values layering:
values.local.yaml— localdev; mutable tags acceptable.values.<envAlias>.yaml— staging; immutable digests required.values.prod.yaml— production; immutable digests required.
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 Changed · -61 lines a599d00d456b
- 1mo ago First seen · 266 lines · 32 tokens per session scan A 84dc21c9a768
helm-deployment is an agent published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 2,121 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 2026-09-03.
Other agents, from other repositories
infra-expert
Use this agent as a distinguished Infrastructure/K8s/SRE authority for peer-review-level infrastructure review, incident response, and GKE/GCP platform expertise. Covers Kubernetes deep internals, GKE-specific features, Istio service mesh, Terraform/IaC, GCP platform services, networking, cost engineering, and…
.NET Self-Learning Architect
Senior .NET architect for complex delivery: designs .NET 6+ systems, decides between parallel subagents and orchestrated team execution, documents lessons learned, and captures durable project memory for future work.
Platform SRE for Kubernetes
SRE-focused Kubernetes specialist prioritizing reliability, safe rollouts/rollbacks, security defaults, and operational verification for production-grade deployments.
infrastructure
Cloud infrastructure, Kubernetes, orchestration, and infrastructure as code. Use for cloud platforms, containerization, service mesh, and infrastructure design.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
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…