route-models SKILL.md skillA

route-models from abhiindigloo/evalharness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add abhiindigloo/evalharness/route-models@git:20261016.b34e048

Pins git:20261016.b34e048 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
abhiindigloo/evalharness
Path
skills/route-models/SKILL.md
Versions recorded
2
Latest version
git:20261016.b34e048, committed Oct 16, 2026
First version recorded
Oct 14, 2026
Size
4,171 bytes
Repository stars
7
License
MIT

Generate a cheapest-first model routing setup with fallbacks and quality escalation, from eval-models results or a user-chosen model order. Produces a standalone Python router (escalates when a reply errors or fails format guards), a routing.json, and a LiteLLM proxy config (error-based fallbacks). Use whenever the user wants model routing, fallbacks, failover, escalation to a stronger model, cost-saving cascades, "use the cheap model unless it fails", or a LiteLLM or gateway config across…

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

# Generate a cheapest-first routing setup

Use evidence to send each request to the cheapest model that is likely to succeed, and escalate only when a failure can be detected.

## Inputs

- **Preferred**: `results.json` from eval-models. The chain is every candidate that met the threshold with a known cost, ordered by cost per passing call, keeping each model only if it is more reliable than the cheaper ones before it (dominated models are dropped and listed).
- **Otherwise**: an explicit order from the user via `--chain id1,id2`. Without eval evidence, say clearly that the order is an untested assumption and recommend running eval-models first.

## Guards: the part that makes escalation useful

Escalation on quality only works if a bad reply can be detected automatically. Ask what every good reply must look like, then write `guards.json`:

```json
{"checks": [{"type": "json_keys", "keys": ["invoice_number", "total"]},
            {"type": "max_chars", "value": 2000}]}
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add abhiindigloo/evalharness/route-models@sha256:4a3c0d36d650afe5

The line at the top of this page pins the label git:20261016.b34e048, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_3hab4axrnaftip6t.svg)](https://markdownregistry.com/a/art_3hab4axrnaftip6t)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Oct 14, 2026 and Oct 16, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261016.b34e048 latest2026-10-16 b34e048 4,171 BA view · diff
git:20261014.4490b682026-10-14 4490b68 3,978 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4171 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

GitHub

abhiindigloo/evalharness · 7 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3hab4axrnaftip6t
GET https://markdownregistry.com/api/v1/resolve?ref=abhiindigloo/evalharness/route-models
GET https://markdownregistry.com/api/v1/blob/4a3c0d36d650afe5c9c30164a4000a180d67c2be60f863e3b309d22f65f1528f

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.

More from abhiindigloo/evalharness

AGENTS.md AGENTS.md file
abhiindigloo/evalharness · AGENTS.md
git:20261016.b34e048 · audit A · 7 stars
DESIGN.md@assets DESIGN.md file
abhiindigloo/evalharness · assets/DESIGN.md
git:20261017.d5c2f0b · audit A · 7 stars
eval-models SKILL.md skill
abhiindigloo/evalharness · skills/eval-models/SKILL.md · Run the user's own examples against several AI models (Claude, Gemini, OpenAI, or any OpenAI-compatible endpoint…
git:20261103.c0363cf · audit A · 7 stars
find-model SKILL.md skill
abhiindigloo/evalharness · skills/find-model/SKILL.md · Compare and recommend AI models across providers (Anthropic Claude, Google Gemini, OpenAI, Bedrock, Vertex AI, Azure…
git:20261016.b34e048 · audit A · 7 stars
size-local-model SKILL.md skill
abhiindigloo/evalharness · skills/size-local-model/SKILL.md · Estimate the GPU or unified memory needed to run an open-weight model locally, covering weights at a given precision or…
git:20261016.b34e048 · audit A · 7 stars

Every file in abhiindigloo/evalharness

Browse by kind, by grade A, or by owner.