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 Tano73/agent-skills --skill smart-routergit clone --depth 1 https://github.com/Tano73/agent-skillsWrote 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/tano73/agent-skills/smart-router)<a href="https://agentmods.dev/skills/tano73/agent-skills/smart-router"><img src="https://agentmods.dev/badge/skills/tano73/agent-skills/smart-router/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.
<a href="https://agentmods.dev/skills/tano73/agent-skills/smart-router"><img src="https://agentmods.dev/badge/skills/tano73/agent-skills/smart-router.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00203 | $0.04565 |
| Opus 5 | $0.00102 | $0.02282 |
| Sonnet 5 | $0.00041 | $0.00913 |
| Haiku 4.5 | $0.00020 | $0.00456 |
Grade A, and why
smart-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 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.
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Router
Route tasks to the most appropriate AI model by spending a tiny amount of cheap-model time upfront to score the task's complexity, then executing with the model best suited to that complexity.
Why this matters
Running every task on the most powerful model wastes money and time. Running everything on cheap models degrades quality. This skill finds the right balance: a small analysis cost buys a much better routing decision.
Architecture (file map)
~/.agents/skills/smart-router/
├── SKILL.md ← this file (the workflow)
├── models.json ← multi-client tier→slug mapping (schema v2)
├── bin/
│ └── router.py ← config CLI (verbs: init/show/use/reset/status/…)
└── evals/
├── evals.json ← test prompts + expected routing
└── scripts/
└── route.py ← offline routing-decision validator
The skill's runtime model selection is runtime-agnostic: it operates on abstract tiers (cheap, balanced, heavy, frontier, code-mid, code-heavy, analyzer). Tier → real slug resolution is delegated to models.json, organized per client (Cursor, Claude Code, Codex CLI, …). The same skill installation can therefore be shared across multiple CLI clients.
How the user invokes this skill
This skill has no session toggle. It runs only when the user explicitly invokes it in the prompt — either to route a task (e.g. "usa lo smart router per…", "route this with the smart router", "scegli tu il modello per…") or to manage the model configuration via one of the verbs below. There is no "always on" mode and no ~/.smart-router.state file: each routing request must be explicit. Do not self-trigger on the bare words "route"/"routing"/"instrada" when they refer to networking or web routes.
Router configuration commands (verbs)
The user can manage the tier→slug configuration by name. Each verb maps 1:1 to a sub-command of router.py. When the user says any of the trigger phrases below, run the corresponding command and surface its output to the user.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 300 lines · 203 tokens per session scan A 5b53e823181d
smart-router is a skill published in the GitHub repository Tano73/agent-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 203 tokens to every session and 4,565 once invoked, about $0.0010 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…