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 OpenLinkSoftware/ai-agent-skills --skill llm-routing-skillgit clone --depth 1 https://github.com/OpenLinkSoftware/ai-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/openlinksoftware/ai-agent-skills/llm-routing-skill)<a href="https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/llm-routing-skill"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/llm-routing-skill/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/openlinksoftware/ai-agent-skills/llm-routing-skill"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/llm-routing-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00140 | $0.04755 |
| Opus 5 | $0.00070 | $0.02377 |
| Sonnet 5 | $0.00028 | $0.00951 |
| Haiku 4.5 | $0.00014 | $0.00475 |
Grade A, and why
llm-routing-skill 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 10d 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Routing Skill
Route tasks and agent sub-steps to the right model — the one that sits on the
cost–quality Pareto frontier for the task's required capability level, under
your cost tier, latency, and governance constraints. The routing intelligence is
a living graph of model capability × cost × latency (RDF-Turtle +
JSON mirror in references/), rebuilt from live pricing feeds whenever
prices change or capability profiles are refined via feedback.
This is the routing contract. Read the whole file before routing; re-read the relevant section before building any routing artifact (Anti-Drift Protocol).
1. Why this exists
A static "always use the biggest model" policy wastes money. A pure cheapest-first policy risks quality failures. The sweet spot is the cost–quality Pareto frontier:
- Map the task (or agent sub-step) to a required capability level.
- Know which models deliver acceptable quality for that capability, at what price and latency — from the routing graph.
- Route simple/repetitive work to efficient models and escalate only when needed (advisor pattern).
The same intelligence powers OpenRouter's Auto Router (task classification +
community share-of-spend + your cost_tier), Snowflake Cortex's dynamic model
routing (approved models + trade-off policies + classifier + advisor), and
RouteLLM-style cascades. This skill makes that intelligence yours:
transparent, queryable, and editable — the graph, the knobs, and the feedback
loop are all first-class artifacts.
2. Architecture
┌──────────────────────────────────────────────┐
│ LLM ROUTING GRAPH │
│ references/routing-graph.ttl (+ .json) │
│ model capability × cost × latency │
│ per task type: Pareto frontier + escalation │
└──────────────────────────────────────────────┘
▲ rebuild │ query
┌──────────────┴─────────────┐ ▼
┌─────┴──────┐ ┌──────────────────┴───┐ ┌───────────────┐
│ PRICES │ │ PROFILES (seeds) │ │ ROUTER │
│ live │ │ capability-profiles │ │ classify task │
│ llm-prices │ │ .json — edit me │ │ pick policy │
│ .com feeds │ │ task-types.json │ │ query graph │
└────────────┘ └──────────────────────┘ │ escalate │
└───────────────┘
What ships with it
15 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.
- CHANGELOG.md 7.3 KB
- examples/routing-example.md 3.4 KB
- README.md 14 KB
- references/capability-profiles.json 19 KB
- references/feedback-log.ttl 1.8 KB
- references/llm-routing-ontology.ttl 17 KB
- references/routing-graph.json 96 KB
- references/routing-graph.ttl 527 KB
- references/task-types.json 8.9 KB
- scripts/build_routing_graph.py 20 KB runs code
- scripts/fetch_prices.py 2.6 KB runs code
- scripts/harvest_traces.py 8.9 KB runs code
- scripts/record_trace.py 7.9 KB runs code
- scripts/route.py 8.2 KB runs code
- scripts/validate_graph.py 8.5 KB runs code
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.
- 10d ago First seen · 402 lines · 140 tokens per session scan A cba8c5413f7f
llm-routing-skill is a skill published in the GitHub repository OpenLinkSoftware/ai-agent-skills (38 stars, last pushed yesterday), licensed MIT. It adds 140 tokens to every session and 4,755 once invoked, about $0.0007 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.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.