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 agentmods add instructions/alexmond/jhelm/claude-mdgit 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/instructions/alexmond/jhelm/claude-md)<a href="https://agentmods.dev/instructions/alexmond/jhelm/claude-md"><img src="https://agentmods.dev/badge/instructions/alexmond/jhelm/claude-md.svg" alt="Measured on agentmods" 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 | $0.02160 | $0.02160 |
| Opus 5 | $0.01080 | $0.01080 |
| Sonnet 5 | $0.00432 | $0.00432 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
jhelm CLAUDE.md 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 4d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - jhelm Project Guide
Project Overview
jhelm is a Java implementation of the Helm package manager for Kubernetes. It provides native Java libraries and tools to work with Helm charts without requiring the Go-based Helm CLI.
Tech Stack: Java 21, Spring Boot 4.0.5, Kubernetes Client 25.0.0, Picocli 4.7.7, Jackson YAML, Lombok
Project Structure
jhelm (parent)
├── jhelm-gotemplate/ — Go template engine (standalone, no Spring)
├── jhelm-gotemplate-sprig/ — Sprig function implementations (ServiceLoader, priority 100)
├── jhelm-gotemplate-helm/ — Helm function implementations (ServiceLoader, priority 200)
├── jhelm-core/ — Helm logic, charts, actions (depends on: gotemplate)
├── jhelm-kube/ — Kubernetes client integration (depends on: core)
├── jhelm-rest/ — REST API module
├── jhelm-plugin/ — Maven plugin for packaging
├── jhelm-cli/ — CLI entry point, Spring Boot + Picocli (depends on: core, kube)
├── jhelm-sample/ — Sample application
├── jhelm-rest-sample/ — REST sample application
└── docs/ — Antora documentation (AsciiDoc)
Build & Test Commands
# Build the project
./mvnw clean install
# Run all tests
./mvnw test
# Run tests for a specific module
./mvnw test -pl jhelm-core
# Run a specific test class
./mvnw test -Dtest=KpsComparisonTest -pl jhelm-core
# Run a specific test method
./mvnw test -Dtest=KpsComparisonTest#testSimpleRendering -pl jhelm-core
Always run relevant tests after making code changes. Fix any test failures before committing.
Coding Standards
Style
- Indentation: Tabs (enforced by
spring-javaformat-maven-plugin) - Formatter:
spring-javaformatruns on everyvalidatephase — run./mvnw spring-javaformat:applyto auto-format - Naming: Classes
PascalCase, methods/variablescamelCase, constantsUPPER_SNAKE_CASE - Imports: Always use
importstatements — never use fully qualified class names inline in code (e.g., useLocale.ROOTnotjava.util.Locale.ROOT). Enforced by PMDUnnecessaryFullyQualifiedNamerule. Fix script:python3 .claude/scripts/fix_fqn.py . - Javadoc: Use HTML tags for links,
{@code true}/{@code false}for booleans, accurate@param/@returntags
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.
- 4d ago First seen · 189 lines · 2,160 tokens per session scan A 4ad738c047ab
jhelm CLAUDE.md is an instructions file published in the GitHub repository alexmond/jhelm (4 stars, last pushed 10d ago), licensed Apache-2.0. It adds 2,160 tokens to every session, about $0.0108 per session on Opus 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 instructions, from other repositories
charts CLAUDE.md
Claude Code instructions for duyet/charts, covering claude.md - project philosophy & development guide, the vision, core principles, 1. simplicity without losing power and 2. consistency is kindness.
mongo-java-driver AGENTS.md
AGENTS.md instructions for mongodb/mongo-java-driver, covering agents.md - mongodb java driver, git, core rules, build and style.
openclaw-operator CLAUDE.md
Claude Code instructions for paperclipinc/openclaw-operator, covering claude.md — openclaw kubernetes operator, project overview, commands, architecture and reconciliation rules.
radar CLAUDE.md
Claude Code instructions for skyhook-io/radar, covering claude.md, project overview, code comments, release and publishing authorization and reference docs — must read before making changes.
toBeBetterJavaer CLAUDE.md
Claude Code instructions for itwanger/toBeBetterJavaer, covering claude.md, 你的形象, 项目概况, 目录地图 and 写作工作流.
toBeBetterJavaer AGENTS.md
AGENTS.md instructions for itwanger/toBeBetterJavaer, covering 工具权限设置, 工具使用规则, 获取网页内容 and 图片生成 / 文章配图.