vellum-ai/vellum-assistant · skills/llm-cost-optimizer/SKILL.md

llm-cost-optimizer skillA

llm-cost-optimizer is agent-read markdown (skill) from vellum-ai/vellum-assistant: Analyze and reduce LLM spend: read usage breakdowns by call site, model, and inference profile, understand single-winner profile resolution, and pin call sites to managed profiles (Balanced / Quality / Budget / Fast) only where they should deviate from shipped defaults..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add vellum-ai/vellum-assistant/llm-cost-optimizer@git:20260901.63b6d83
Exact content
mdr add vellum-ai/vellum-assistant/llm-cost-optimizer@sha256:e57dc0405c50a5ad

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_6hck2g3e6x4ljiuh.svg)](https://markdownregistry.com/a/art_6hck2g3e6x4ljiuh)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260901.63b6d83 latest2026-09-01 63b6d83 15,825 BA view · diff
git:20260804.c3f07752026-08-04 c3f0775 15,821 BA view · diff
git:20260803.3a7ba232026-08-03 3a7ba23 15,590 BA view · diff
git:20260728.c81c65f2026-07-28 c81c65f 15,316 BA view · diff
git:20260710.4eb47ce2026-07-10 4eb47ce 13,324 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (15825 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

vellum-ai/vellum-assistant · 1,277 stars · license MIT · pushed 2026-09-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6hck2g3e6x4ljiuh
GET https://markdownregistry.com/api/v1/resolve?ref=vellum-ai/vellum-assistant/llm-cost-optimizer
GET https://markdownregistry.com/api/v1/blob/e57dc0405c50a5ad822a164d6dea6201565151e0edc2093bf79f46d3fefb4161

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.