helm-zabbix: Skill for Claude Code

.agents/skills/release-chart/SKILL.md

release-chart is a skill for Claude Code, Codex from zabbix-community/helm-zabbix. It costs 108 tokens per session (1,584 once invoked), scanned A, original, Apache-2.0.

A release workflow for the Zabbix Helm chart, a package that installs Zabbix on Kubernetes using Helm.

In plain words
What is it for?
Use it to prepare a chart release by updating its files, regenerating documentation, and tagging the version after confirming the release actions.
Why use it?
It guides maintainers through the required version updates, documentation generation, and release steps while highlighting actions that publish changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is zabbix-community/helm-zabbix's own configuration. It tells Claude Code and Codex how to work on helm-zabbix itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything helm-zabbix configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is ln -s ../../.agents/skills/release-chart .claude/skills/release-chart.

Reuse

Borrowing it

Nothing to install: this file belongs to zabbix-community/helm-zabbix. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zabbix-community/helm-zabbix/main/.agents/skills/release-chart/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zabbix-community/helm-zabbix

Made for: Claude Code, Codex.

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 release-chart

README.md
[![agentmods](https://agentmods.dev/badge/skills/zabbix-community/helm-zabbix/release-chart/github.svg)](https://agentmods.dev/skills/zabbix-community/helm-zabbix/release-chart)
Your own site
<a href="https://agentmods.dev/skills/zabbix-community/helm-zabbix/release-chart"><img src="https://agentmods.dev/badge/skills/zabbix-community/helm-zabbix/release-chart/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.

agentmods 80×15 button for release-chart

Your own site · 80×15
<a href="https://agentmods.dev/skills/zabbix-community/helm-zabbix/release-chart"><img src="https://agentmods.dev/badge/skills/zabbix-community/helm-zabbix/release-chart.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,584 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 8
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Agent Snooping · line 12
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 16
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Rogue Agent · line 16
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Agent Snooping · line 21
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 5.1 $0.00108 $0.01584
Opus 5 $0.00054 $0.00792
Sonnet 5 $0.00022 $0.00317
Haiku 4.5 $0.00011 $0.00158

Measured 9d ago against content hash b28c51b329d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release-chart 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 9d 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.

.agents/skills/release-chart/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release a new version of the helm-zabbix chart

This skill walks through the maintainer-only release process documented in CONTRIBUTING.md ("For code mainteners only") and CLAUDE.md ("Versioning and release rules"). Its final steps are hard to reverse — pushing a git tag triggers a public GitHub Release via CI — so always confirm the version number and each push/tag/PR action with the user before running it. Do not skip confirmation because a step "seems obvious".

Installing and invoking this skill

This repo keeps skills under .agents/skills/ rather than .claude/skills/ so the same file can be reused by any AI assistant that supports a skills convention, not just Claude Code. To get Claude Code's native /release-chart invocation, symlink this directory in:

  • Project-level (this repo only):
    mkdir -p .claude/skills
    ln -s ../../.agents/skills/release-chart .claude/skills/release-chart
    
  • Personal (available in every repo you work in):
    mkdir -p ~/.claude/skills
    ln -s /absolute/path/to/helm-zabbix/.agents/skills/release-chart ~/.claude/skills/release-chart
    

Once linked, run it with /release-chart, or just describe the task in natural language — e.g. "release a new chart version", "cut a release", "bump the chart version", "prepare the next Zabbix chart release" (these phrases match the description frontmatter above).

No symlink is strictly required to benefit from this file: CLAUDE.md already tells Claude Code to read and follow it whenever a maintainer asks to cut/publish a release, so it works out of the box in this repo. The symlink is only needed for the formal /release-chart slash invocation or to reuse the skill from other repositories.

0. Preconditions

  • Confirm with the user (if not already given):
    • The new chart version (and whether appVersion/zabbixImageTag — the Zabbix version — is also changing).
    • Whether this is a major bump (the middle digit, e.g. 7.0.127.1.0 — signals a change that may require users to update their values.yaml) or a minor bump (the last digit, e.g. 7.0.127.0.13 — no API/interface changes).
  • Verify all PRs intended for this release are already merged into main, and local main is up to date.
  • Never bump versions or tag directly on main — always use a release branch.

Read the full file on GitHub · 112 lines

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. 9d ago First seen · 112 lines · 108 tokens per session scan A b28c51b329d5

Subscribe to this mod's changes

release-chart is a skill published in the GitHub repository zabbix-community/helm-zabbix (129 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 108 tokens to every session and 1,584 once invoked, about $0.0005 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 2026-08-30.