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 JansenAnalytics/claudex --skill model-routergit clone --depth 1 https://github.com/JansenAnalytics/claudexWrote 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/jansenanalytics/claudex/model-router)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/model-router"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/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 | $0.00049 | $0.00561 |
| Opus 5 | $0.00024 | $0.00280 |
| Sonnet 5 | $0.00010 | $0.00112 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
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 3d 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.
What it actually says
Model Router Skill
Use EVERY TIME you are about to spawn a sub-agent or do significant work. Classify the task first, then use the right model tier.
Step 1: Classify
node ${MODEL_ROUTER_HOME:-$HOME/projects/model-router}/classify.cjs "your task description here"
Or get JSON for scripting:
node ${MODEL_ROUTER_HOME:-$HOME/projects/model-router}/classify.cjs --json "task description"
Step 2: Spawn with the recommended model
sessions_spawn(task=..., model="<model from classifier>")
Step 3: Log usage (optional but encouraged)
node ${MODEL_ROUTER_HOME:-$HOME/projects/model-router}/log-usage.cjs --task "..." --tier fast --model "..."
Tier guide
fast — anthropic/claude-haiku-4-5
Use for: summarize, format, extract, classify, convert, translate, clean data, rename, sort, filter Cost: ~1× baseline When in doubt about simple tasks, start here.
balanced — anthropic/claude-sonnet-4-6 (default)
Use for: explain, compare, draft, review, outline, moderate analysis, code with clear spec Cost: ~15× baseline
powerful — anthropic/claude-opus-4-5
Use for: deep analysis, architecture decisions, complex tradeoffs, research synthesis, debates, long-form strategy Cost: ~75× baseline Reserve for tasks where quality clearly matters more than speed/cost.
Classification signals
Fast triggers: summarize, format, extract, classify, categorize, convert, translate, list, count, clean, parse, fix typos, rename, sort, filter, deduplicate, "quick", "simple", "brief", "just"
Powerful triggers: "analyze deeply", architecture, tradeoffs, debate, hypothesis, synthesize, "design system", "evaluate options", comprehensive, thorough, research, strategy, critique, multiple complex questions
Usage stats
node ${MODEL_ROUTER_HOME:-$HOME/projects/model-router}/usage-report.cjs
node ${MODEL_ROUTER_HOME:-$HOME/projects/model-router}/usage-report.cjs --days 30
What ships with it
1 file 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.
- 3d ago First seen · 68 lines · 49 tokens per session scan A b07228380d9e
model-router is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 561 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
uctm-init
An initialization procedure for uc-taskmanager, a project task-management pipeline. It creates a works directory and, with permission, adds the file and command access the agent needs to local settings.
work-pipeline
Triggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use this skill whenever you detect a [] tag at the beginning of a user message.
feature-spec
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
implement-feature
Implements a feature from its specification. Reads the spec, designs architecture, writes code and tests. Delegates to the Forja (Dev) agent.