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 alexmond/jhelm --skill architecturegit clone --depth 1 https://github.com/alexmond/jhelmWrote 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/alexmond/jhelm/architecture)<a href="https://agentmods.dev/skills/alexmond/jhelm/architecture"><img src="https://agentmods.dev/badge/skills/alexmond/jhelm/architecture/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/alexmond/jhelm/architecture"><img src="https://agentmods.dev/badge/skills/alexmond/jhelm/architecture.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 | $0.00014 | $0.00388 |
| Opus 5.5 | $0.00006 | $0.00155 |
| Sonnet 5.5 | $0.00003 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
architecture 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.
What it actually says
jhelm Architecture
Java 21 | Spring Boot 4.0.2 | Kubernetes Client 25.0.0 | Picocli 4.7.6
Module Dependency Graph
jhelm (parent)
├── jhelm-gotemplate — Go template engine (standalone, no Spring)
├── jhelm-core — Helm logic, charts, actions (depends on: gotemplate)
├── jhelm-kube — Kubernetes client integration (depends on: core)
└── jhelm-cli — CLI, Spring Boot + Picocli (depends on: core, kube)
Template Engine (jhelm-gotemplate)
- Pipeline: Lexer → Parser → AST → Executor
- Key classes:
GoTemplate,GoTemplateFactory,Functions - Functions by category: Sprig (strings, collections, logic, math, encoding, crypto, date, reflection, network, semver) and Helm (conversion, template, kubernetes, chart)
- No Spring dependency — pure Java library
Core Engine (jhelm-core)
Engine.java— Orchestrates template processingChart.java— Represents Helm charts with metadata and templatesRepoManager.java— Manages chart repositories- Creates new
GoTemplateFactoryper render to avoid template accumulation - Stack depth tracking prevents infinite template recursion
Kubernetes Integration (jhelm-kube)
HelmKubeService— Kubernetes resource deployment- Uses official Kubernetes Java Client 25.0.0
CLI Application (jhelm-cli)
- Spring Boot 4.0.2 application
- Picocli-based command structure
- Entry point for user-facing commands
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 · 41 lines · 14 tokens per session scan A a0b39a5fef68
architecture is a skill published in the GitHub repository alexmond/jhelm (7 stars, last pushed 3d ago), licensed Apache-2.0. It adds 14 tokens to every session and 388 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 2026-08-31.
Other skills, from other repositories
zhihu-search
A search skill for finding content on Zhihu, a Chinese question-and-answer and article platform, through its search API.
aws-cloudformation-lambda
Provides AWS CloudFormation patterns for Lambda functions, layers, API Gateway integration, event sources, cold start optimization, monitoring, logging, template validation, and deployment workflows. Use when creating Lambda functions with CloudFormation, configuring event sources, implementing cold start…
java-expert
Expert-level Java development with Java 21+ features, Spring Boot, Maven/Gradle, and enterprise best practices. Use when the user mentions JVM, Spring, Maven, Gradle, or enterprise, or when the task involves Modern Java, Spring Boot, Build Tools, or Dependency Injection.
quarkus-backend
Use this skill when building Quarkus backend applications — supersonic Java, Dev UI, GraalVM native, reactive messaging, Panache ORM. This skill enforces: compile-time metadata processing, live reload, continuous testing, container-first design. Do NOT use for: Spring Boot projects, Micronaut applications, standard…
quarkus-kubernetes-native
Deploy container-first Quarkus applications on Kubernetes with fast startup, low memory, native images, and health probes. Use when Quarkus is chosen specifically for cloud/Kubernetes efficiency over Spring Boot.
aws-fullstack-development
Apply AWS-oriented fullstack defaults for frontend hosting, backend microservices, security, and observability. Use when users request cloud-specific fullstack delivery on AWS.