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 sykoramade/helm-skill --skill helm-update-checkgit clone --depth 1 https://github.com/sykoramade/helm-skillWrote 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/sykoramade/helm-skill/helm-update-check)<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-update-check"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-update-check.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 5.1 | $0.00078 | $0.00934 |
| Opus 5 | $0.00039 | $0.00467 |
| Sonnet 5 | $0.00016 | $0.00187 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
helm-update-check scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `WebFetch` / `curl -s https://raw.githubusercontent.com/sykoramade/helm-skill/main/.claude-plugin/plugin.json` and parse `version`. How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HELM Update Check
HELM ships as markdown, so there is no background updater. Instead, the entry-point skills run this check once at the start of a session: compare the installed version to the latest published version and, if you're behind, hand the MD the exact one-liner to update. It checks and recommends automatically; it never changes the install (that is the MD's
/plugincommand to run).
When to run
- Once per session, as Step 0 of
helm-orchestrator,helm-onboarding, orhelm-portfolio— whichever the MD enters through. If the check already ran this session, skip it. - It must never block work. Run it, surface a single line if an update
exists, and continue. If anything fails (offline, no
gh, rate-limited), skip silently — no error to the MD.
The check (mechanical)
-
Read the installed version. Read the
versionfield from this pack's own.claude-plugin/plugin.json(it ships next to theskills/directory). Call itINSTALLED. -
Fetch the latest version. Read the same field from the repo's
main, using whatever the host has:gh api repos/sykoramade/helm-skill/contents/.claude-plugin/plugin.json --jq '.content' | base64 -d(then parseversion), orWebFetch/curl -s https://raw.githubusercontent.com/sykoramade/helm-skill/main/.claude-plugin/plugin.jsonand parseversion.
Call it
LATEST. If neither path is available or the fetch fails, stop here silently — no network, no nag. (On a host withoutgh,WebFetch, orcurl— e.g. a plain system prompt — the check is simply a no-op; it never errors and never blocks, consistent with HELM's local-first, no-dependency promise.) -
Compare as semver (
MAJOR.MINOR.PATCH, numeric component by component).LATEST == INSTALLED→ up to date. Say nothing (or, only if the MD asked "am I current?", confirm in one line).LATEST > INSTALLED→ an update is available. Surface the recommendation (below).LATEST < INSTALLED→ you're ahead ofmain(a dev build); say nothing.
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.
- 8d ago First seen · 72 lines · 78 tokens per session scan A 2bb0418cb625
helm-update-check is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 934 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…