agentleFS
Sign inStart free
uniqaiappuniqaiapp/model-router/AGENTS.md

model-router

AGENTS.md0 starsChanged 15 days agoMITView on GitHub

This repository is an agent skill: model-router picks the cheapest LLM tier (fast / smart / premium) that can do a task, recommends a model per provider and estimates the cost before you run it. The full instructions are in SKILL.md; read it first. Copy or clone this repo, then follow "Install" in README.md. When the user asks which model to use, how much a prompt or batch will cost, or wants to cut LLM spend, follow SKILL.md: classify the…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository2 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run tests: node tests/run.mjs.

    line 8
  2. Very specific:

    Keep SKILL.md under 500 lines.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md

This repository is an agent skill: model-router picks the cheapest LLM tier (fast / smart / premium) that can do a task, recommends a model per provider and estimates the cost before you run it. The full instructions are in SKILL.md; read it first.

Working in this repo

  • Zero dependencies: Node 18+ built-ins only. Do not add packages, a package.json with dependencies, or a lockfile.
  • Run tests: node tests/run.mjs. Validate the price table: node scripts/check.mjs.
  • Prices live only in data/prices.json. Every row has a source URL and a checked date. Never type a price into Markdown by hand; references/price-table.md is generated by node scripts/table.mjs --write.
  • examples/expected/* are produced by the scripts and compared byte-for-byte in tests. Regenerate with node scripts/regen-examples.mjs after changing rules or prices.
  • Keep SKILL.md under 500 lines; long material goes to references/.
  • Author and maintainer is UniqAI support@uniqai.app; do not add personal names anywhere.

Using this skill from another project

Copy or clone this repo, then follow "Install" in README.md. When the user asks which model to use, how much a prompt or batch will cost, or wants to cut LLM spend, follow SKILL.md: classify the task, pick the tier, run scripts/cost.mjs for the estimate, and show the reasons.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free