helm-compat-checker

helm-compat-checker is an agent for Claude Code from alexmond/jhelm. It costs 25 tokens per session (334 once invoked), scanned A, original, Apache-2.0.

A comparison agent that checks whether jhelm renders a Helm chart the same way as Go Helm, the original Helm implementation. It reports differences and helps classify them as bugs, harmless formatting changes, or known exceptions.

In plain words
What is it for?
Comparing one chart’s rendered templates, reviewing output differences, and recording differences that are expected or already understood.
Why use it?
It finds compatibility problems that ordinary unit tests may miss when jhelm processes real charts. This helps confirm that charts behave consistently across both implementations.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/alexmond/jhelm/helm-compat-checker
Clone the repo
git clone --depth 1 https://github.com/alexmond/jhelm

Made for: Claude Code.

Wrote 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.

agentmods badge for helm-compat-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmond/jhelm/helm-compat-checker.svg)](https://agentmods.dev/agents/alexmond/jhelm/helm-compat-checker)
Your own site
<a href="https://agentmods.dev/agents/alexmond/jhelm/helm-compat-checker"><img src="https://agentmods.dev/badge/agents/alexmond/jhelm/helm-compat-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 334 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00334
Opus 5 $0.00013 $0.00167
Sonnet 5 $0.00005 $0.00067
Haiku 4.5 $0.00003 $0.00033

Measured 5d ago against content hash c708235b0e44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

helm-compat-checker 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 5d 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.

.claude/agents/helm-compat-checker.md · 36 lines

What it actually says

You are a Helm compatibility checker for the jhelm project at /Users/alex.mondshain/claude/jhelm.

Your Job

Compare jhelm's template rendering output against Go Helm's output for a given chart.

How to Check

  1. Single chart mode: Write chartName,repoId,repoUrl to jhelm-core/src/test/resources/single.csv
  2. Run comparison: ./mvnw test -Dtest=KpsComparisonTest#compareSingleChart -pl jhelm-core
  3. Check results in target/surefire-reports/KpsComparisonTest.txt
  4. If differences found: analyze whether they are:
    • Real bugs in jhelm (report with file/line)
    • Acceptable differences (whitespace, comment ordering)
    • Already tracked in comparison-ignores.yaml

Comparison Ignores

File: jhelm-core/src/test/resources/comparison-ignores.yaml

When a difference is expected/known, it should have an ignore rule with a clear reason.

Report Format

  • Chart name and version tested
  • Number of templates compared
  • Differences found (if any), with template name and diff snippet
  • Whether each difference is a bug, acceptable, or already ignored
Changes

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.

  1. 5d ago First seen · 36 lines · 25 tokens per session scan A c708235b0e44

Subscribe to this mod's changes

helm-compat-checker is an agent published in the GitHub repository alexmond/jhelm (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 25 tokens to every session and 334 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

dependency-browser

Extracts a Maven dependency's JAR (or sources JAR) into the project build dir so you can browse its classes and source. Use when you need to explore the API or internals of a library. Pass coordinates as group:artifact:version or group:artifact:version:sources. Omit version to have it looked up from…

jonapoul/aktual · 83 tokens

java-reviewer

Review Java code changes against OpenMetadata backend patterns and Kafka-grade quality standards — method size limits, IntelliJ-level inspections, immutability, granular error handling, and human-readable code.

open-metadata/OpenMetadata · 40 tokens

plinth-architect

Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.

jabrena/plinth · 38 tokens

plinth-java-coder

Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.

jabrena/plinth · 29 tokens

java-security-expert

Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and…

giuseppe-trisciuoglio/developer-kit · 85 tokens

java-pro

Master modern Java with streams, concurrency, and JVM optimization. Handles Spring Boot, reactive programming, and enterprise patterns. Use PROACTIVELY for Java performance tuning, concurrent programming, or complex enterprise solutions.

echoVic/blade-code · 44 tokens