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-model-routergit 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-model-router)<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-model-router"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-model-router.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 | $0.00111 | $0.03342 |
| Opus 5 | $0.00056 | $0.01671 |
| Sonnet 5 | $0.00022 | $0.00668 |
| Haiku 4.5 | $0.00011 | $0.00334 |
Grade A, and why
helm-model-router 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 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.
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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HELM Model Router
A frontier model is expensive. Most tasks in a real project don't need one. This skill lets the CEO score each task, send it to the cheapest model that can actually do it, and escalate only when a cheaper model falls short — so the expensive model is the exception, not the default.
It's model-agnostic and you own the lineup. Run everything locally for $0, mix in a cheap hosted model, add a frontier model as the safety net — any model that speaks the OpenAI-compatible API works, and you set cost and capability per model.
The principle in one line: never pay for capability you don't need, but never ship a result a cheap model got wrong.
0. What this skill is (and is not) — read this first
HELM ships as markdown, not a service. So this router is what the host (the CEO running in Claude Code, Cursor, etc.) can do with a config file and the host's own tool/shell access: read your model lineup, score a task against rules you can read, call the cheapest capable model, and escalate on failure. It is deterministic and inspectable — the same task scores the same way every time, and the CEO states the reason it picked a model.
What it deliberately does not do in the markdown pack: keep a live circuit breaker, learn capability scores from history, or auto-calibrate thresholds over time. Those need a persistent running process, which a skill pack is not — they belong to the full HELM engine (v2) and are flagged as such in §9. This skill claims only what markdown + the host can honestly execute.
┌───────────────────────────────────────┐
task ─────▶ │ 1. SCORE confidence 0.0–1.0 │
│ 2. FILTER drop models below the │
│ capability bar for this │
│ task type │
│ 3. ROUTE score → cheapest capable │
│ 4. EXECUTE call that model │
│ 5. GATE accept only if it passes │
│ 6. ESCALATE on failure, go stronger │
│ 7. LOG record the choice │
└───────────────────────────────────────┘
cheapest ◀──────────────────────────────▶ most capable
local-small ($0) → local-large → cloud-cheap → cloud-strong → frontier
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 · 288 lines · 111 tokens per session scan A 3584cc0ba214
helm-model-router is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 3,342 once invoked, about $0.0006 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 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…