Workflow·AI & Agents·v1.0.0

route-models Agent Skill

Test candidate AI models on your own examples: pass rate, latency, cost.

Context cost
1.1k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 4.2 kBtext throughout, nothing executable
Licence
MITthe author’s own terms
Last change
16 days agov1.0.0
Servers it uses
Noneruns standalone

What it does

Test candidate AI models on your own examples: pass rate, latency, cost.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

Workflow

Runs a procedure end to end.

Filed under

AI & Agents

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md4.2 kB · preview
--- name: route-models metadata: author: Indigloo homepage: https://github.com/Abhiindigloo/EvalHarness ---
9# Generate a cheapest-first routing setup
10
11Use evidence to send each request to the cheapest model that is likely to succeed, and escalate only when a failure can be detected.
12
13## Inputs
14
15- **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).
16- **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.
17
18## Guards: the part that makes escalation useful
19
20Escalation on quality only works if a bad reply can be detected automatically. Ask what every good reply must look like, then write guards.json:
21
22```json
23{"checks": [{"type": "json_keys", "keys": ["invoice_number", "total"]},
24 {"type": "max_chars", "value": 2000}]}
25```
26
27Guards run on every request, so they must be generic (format, required fields, forbidden phrases, length), not the per-example answers used in the eval. Check types match eval-models (contains, not_contains, exact, regex, json_keys, max_chars). Without guards, the router escalates only on errors and empty replies; state that limitation.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md582 words
Files1
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈180
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
870
on trigger
The instruction body, read only when the skill fires.
0.53%
of a 200k window
Ten skills this size would take about 5% of the window before you open a file.
050k100k150k200k context window

1.1k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Small enough to keep loaded permanently without thinking about it.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 4.2 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md4.2 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# route-models · 1.1k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/route-models/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/route-models" ] && { [ ! -e .claude/skills/route-models ] || { mv .claude/skills/route-models "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/route-models" .claude/skills/ && echo "Installed .claude/skills/route-models"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add indigloo/route-models

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/route-models/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/route-models/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/route-models" ] && { [ ! -e ~/.claude/skills/route-models ] || { mv ~/.claude/skills/route-models "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/route-models" ~/.claude/skills/ && echo "Installed ~/.claude/skills/route-models" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/route-models/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version1.0.0
Published16 days ago
PriceFree
Referenceindigloo/route-models

Versions

v1.0.0 shipped 16 days ago. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.0.0
20 Oct 2026
  • The version this listing went live with, after review.
Pinning

The install command always fetches the release that is current the day you run it — v1.0.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers1