helm · Helm

Helm CLI for AI Agents

Render, inspect, install, and upgrade Kubernetes packages with preview and rollback paths.

Official toolOperational risk: R0–R3docs-verified

Install for an Agent Report broken data

Agent readiness

85/100

Evidence confidence

docs-verified

Documentation checked

2026-07-10

Independently tested version

Not independently tested

Install for an Agent

Choose an official installation path that matches the runtime. Pin a version for team or CI use, then record the version before the first task.

HomebrewRecommended

macos · linux

$ shell

brew install helm

winget

windows

$ shell

winget install Helm.Helm

Authentication and Minimum Permissions

Grant only the permissions the task needs. Pass credentials through environment variables or a platform secret store, never through prompts, repositories, or logs.

Authentication requiredHeadless authentication supported

Use read-only cluster credentials for template and list; elevate only for an approved release.

Methods: kubeconfig, registry credentials
Secret environment variables: KUBECONFIG, HELM_REGISTRY_CONFIG
Credential storage: For headless runs, inject KUBECONFIG, HELM_REGISTRY_CONFIG from the CI or platform secret manager at process start. For local interactive use, prefer the CLI or operating-system credential store when the official client supports one. Never save values in repository files.

Agent and Environment Compatibility

Confirm shell access first, then check the platform, network boundary, and credential path.

claude-codecodexgemini-clicopilot-cli

Environments: local, ci, container, headless, remote
Platforms: macos, linux, windows

Structured Output for Reliable Automation

Prefer a machine-readable format. Treat stdout as the result channel and stderr as diagnostics so the agent can parse failures separately.

json · yaml · text

Use --output json where supported and keep diagnostic logs on stderr.

--output json

No independently captured output sample

Structured-output support currently comes from official documentation. CLI Finder does not show a guessed example or invented schema before a bounded, non-destructive execution captures stdout.

R0–R3 Command Risk Guide

Risk is assigned per command. R0 is local or remote read-only, R1 is reversible local write, R2 changes remote state, and R3 can be irreversible or production-impacting.

Read-only does not mean public

R0 only means the command does not change local or remote state. A read-only command may still return secrets, identity data, configuration, or production data. Expose only the minimum needed for the task, and never place it in logs, prompts, or commits.

R0Render a chart locally

Renders manifests without changing cluster state.

$ shell

helm template RELEASE CHART --values values.yaml

Idempotent

R0Preview an upgrade

Renders and validates an upgrade before applying it.

$ shell

helm upgrade RELEASE CHART --dry-run --debug

Idempotent

R2Upgrade a release

Changes live Kubernetes resources.

$ shell

helm upgrade RELEASE CHART --atomic

Confirmation requiredMay repeat a change

R3Uninstall a release

Deletes resources managed by a release.

$ shell

helm uninstall RELEASE

Confirmation requiredMay repeat a change

How the Agent Readiness Score Is Built

Readiness describes how reliably an agent can operate the tool. It does not make every command safe and it does not replace an independent execution test.

Documentation indicates an agent-readiness score of 85/100. No local execution test has been recorded.

Structured output

Use --output json where supported and keep diagnostic logs on stderr.

16/20

Headless operation

Official documentation describes a non-interactive authentication or execution path.

14/15

Safety controls

The documented command surface includes a dry-run, preview, plan, or check path.

14/15

Determinism

Commands use explicit arguments and documented output controls where available.

8/10

Authentication

Use read-only cluster credentials for template and list; elevate only for an approved release.

8/10

Documentation

This entry cites official documentation checked on 2026-07-10.

9/10

Installation

Official installation paths cover macOS, Linux, and Windows.

8/8

Maintenance

An official source repository is linked for release and maintenance review.

6/7

Agent artifacts

CLI Finder can generate registry-derived skills and policies; the tool itself was not credited with shipping them.

2/5

Generate a Skill or Agent Policy

Choose an agent and safety mode to generate a copyable artifact with installation, allowed commands, approval boundaries, and the evidence limitation.

Artifact typeTarget agentSafety mode

Generated artifact preview

SKILL.md

---
name: helm-agent-workflow
description: Use Helm CLI for Helm charts, manifest rendering, release history with explicit command risk and evidence boundaries.
---

# Helm CLI agent workflow

Use this skill when the task needs Helm charts, manifest rendering, release history, Kubernetes upgrades.

## Evidence boundary

- Registry confidence: `docs-verified`
- Documentation checked: `2026-07-10`
- Locally tested version: `not tested`
- Do not describe this CLI as locally verified until its commands have actually been executed in an isolated environment.

## Executed smoke checks

- No local execution record is available.

## Installation

- Homebrew (macos, linux): `brew install helm`
- winget (windows): `winget install Helm.Helm`

## Authentication

- Methods: kubeconfig, registry credentials
- Secret environment variables: `KUBECONFIG`, `HELM_REGISTRY_CONFIG`
- Minimum permissions: Use read-only cluster credentials for template and list; elevate only for an approved release.
- Credential storage: For headless runs, inject KUBECONFIG, HELM_REGISTRY_CONFIG from the CI or platform secret manager at process start. For local interactive use, prefer the CLI or operating-system credential store when the official client supports one. Never save values in repository files.
- Never print, persist, or commit credential values.

## Allowed commands (read-only)

- `helm template RELEASE CHART --values values.yaml` — R0: Renders manifests without changing cluster state.
- `helm upgrade RELEASE CHART --dry-run --debug` — R0: Renders and validates an upgrade before applying it.

## Commands requiring explicit approval (read-only)

- None recorded.

## Forbidden commands (read-only)

- R2 `helm upgrade RELEASE CHART --atomic` — Changes live Kubernetes resources.
- R3 `helm uninstall RELEASE` — Deletes resources managed by a release.

## Execution rules

1. Mode boundary: R0 exact commands may be used; R1, R2, and R3 commands are forbidden.
2. Confirm the selected account, project, context, database, namespace, or environment before any command.
3. Prefer structured output using `--output json`.
4. Capture the exact command, exit code, stdout, and stderr separately.
5. A generated prefix policy must prompt unless that exact prefix is explicitly marked suffix-safe; do not infer safety from the executable name.
6. Never broaden credentials or disable safety controls to make a command succeed.

## Official sources

- [Helm CLI documentation](https://helm.sh/docs/helm/)
- [Helm CLI documentation source repository](https://github.com/helm/helm)

CLI vs MCP vs API for This Task

CLI

Use the CLI on a developer machine, in CI, or in a container when the task should reuse existing shell state, credentials, and scripts and remain directly observable.

MCP

Consider MCP when the agent benefits from controlled tool definitions, delegated identity, or centrally governed server-side access.

API

Use the direct API for persistent application integrations, high-volume requests, or event-driven work where starting a process adds unnecessary overhead.

Read the full CLI vs MCP guide

Verification History and Official Evidence

CLI Finder records documentation review separately from real execution. Installation, help, exit codes, and output cannot be called Verified until they were run.

Current evidence boundary

Official documentation was reviewed, but installation, help output, exit codes, headless behavior, and structured output were not executed locally.