model-routing SKILL.md skillA
model-routing from aquegen/model-routing is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add aquegen/model-routing/model-routing@git:20261022.66c640cPins git:20261022.66c640c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- aquegen/model-routing
- Path
skills/model-routing/SKILL.md- Versions recorded
- 9
- Latest version
- git:20261022.66c640c, committed Oct 22, 2026
- First version recorded
- Sep 10, 2026
- Size
- 39,881 bytes
- Repository stars
- 4
- License
- MIT
Route work to the cheapest model tier that holds quality. Use when deciding which model or agent should handle a task, when the user asks about token economy / cost optimization, or when dispatching implementation, review, or test-run work to subagents.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Model Routing The expensive model thinks, cheaper models grind. The main-session model cannot be switched by Claude - routing works through subagent delegation (the `model` param of the Agent tool, or the agents bundled with this plugin). **Routing makes a dispatch cheaper; it does not make dispatching cheap.** A subagent starts empty, so everything it reads is a cache write, while the main session pays cache read - 12.5x less, 25x on Opus 5.5 and Sonnet 5.5, 50x on Fable 5.1 and Mythos 5.1 - for context it already holds. That penalty is paid whether or not the tier is routed down, so the rules below only pay off on work that was going to be delegated anyway. On one wide-reading session, three runs: doing it inline cost $1.36 and delegating with the tier routed down $1.68, both measured; delegating at the session tier comes to $2.01, which is those same measured subagent tokens repriced at the higher tier rather than a run of its own. Route every dispatch - roughly a sixth off work already leaving the session - and do not manufacture dispatches to collect it. ## Tiers Think in tiers, not model names - names rot, tiers do not: …
Read the whole file at its exact version.
How to install
mdr add aquegen/model-routing/model-routing@sha256:32e1d5f2fa29f3b1The line at the top of this page pins the label git:20261022.66c640c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_mqdud4knrsh7lrox)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Sep 10, 2026 and Oct 22, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261022.66c640c latest | 2026-10-22 | 66c640c | 39,881 B | A | view · diff |
| git:20261013.a3cf7f5 | 2026-10-13 | a3cf7f5 | 37,894 B | A | view · diff |
| git:20261002.c491224 | 2026-10-02 | c491224 | 37,938 B | A | view · diff |
| git:20260929.fde13c8 | 2026-09-29 | fde13c8 | 38,672 B | A | view · diff |
| git:20260922.f074b54 | 2026-09-22 | f074b54 | 29,814 B | A | view · diff |
| git:20260917.14b38b9 | 2026-09-17 | 14b38b9 | 29,357 B | A | view · diff |
| git:20260910.f4ca263 | 2026-09-10 | f4ca263 | 27,778 B | A | view · diff |
| git:20260910.66fafa0 | 2026-09-10 | 66fafa0 | 27,499 B | A | view · diff |
| git:20260910.529e281 | 2026-09-10 | 529e281 | 27,544 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (39881 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
aquegen/model-routing · 4 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_mqdud4knrsh7lrox GET https://markdownregistry.com/api/v1/resolve?ref=aquegen/model-routing/model-routing GET https://markdownregistry.com/api/v1/blob/32e1d5f2fa29f3b1e238734de6267fd9a297ba210fcc01c90a4cd6a0edf05327
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.