llm-cost-optimizer SKILL.md skillA

llm-cost-optimizer from vargasjr-dev/mycadet-temp is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add vargasjr-dev/mycadet-temp/llm-cost-optimizer@git:20261011.59db167

Pins git:20261011.59db167 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
vargasjr-dev/mycadet-temp
Path
skills/llm-cost-optimizer/SKILL.md
Versions recorded
5
Latest version
git:20261011.59db167, committed Oct 11, 2026
First version recorded
Aug 4, 2026
Size
15,805 bytes
Repository stars
47
License
MIT

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 cloud profiles (Balanced / Quality / Budget / Fast) only where they should deviate from shipped defaults.

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

## Overview

This skill walks through analyzing and reducing LLM spend on a Cadet assistant. There are three layers:

1. **Provider connections** — named auth configs (e.g. `anthropic-managed`, `my-personal-key`)
2. **Model profiles** — named presets (provider + model + effort + thinking + contextWindow). Four managed defaults, with UI labels. Note that the keys do not track the labels: read the key, not the name, when pinning a call site.
   - `balanced` → **Balanced** (the general agent-loop profile)
   - `quality-optimized` → **Quality** (the expensive escalation profile)
   - `cost-optimized` → **Budget** (the cheap utility/background profile, and the one to pin for spend reduction)
   - `latency-optimized` → **Fast** (the low time-to-first-token profile, used by live voice; faster but not cheaper than Budget)
3. **Call-site profile pins** (`llm.callSites.<id>.profile`) — optional per-task overrides of the shipped defaults.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add vargasjr-dev/mycadet-temp/llm-cost-optimizer@sha256:a564b7565e4c5563

The line at the top of this page pins the label git:20261011.59db167, 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_2k2fjsnlud2x2h6n.svg)](https://markdownregistry.com/a/art_2k2fjsnlud2x2h6n)

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

Versions

The registry has recorded 5 versions of this file, between Aug 4, 2026 and Oct 11, 2026, about one every 17 days.

versioncommittedcommitsizeaudit
git:20261011.59db167 latest2026-10-11 59db167 15,805 BA view · diff
git:20261007.09b94d22026-10-07 09b94d2 15,821 BA view · diff
git:20261007.cbfc3972026-10-07 cbfc397 15,824 BA view · diff
git:20260901.63b6d832026-09-01 63b6d83 15,825 BA view · diff
git:20260804.c3f07752026-08-04 c3f0775 15,821 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 (15805 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

vargasjr-dev/mycadet-temp · 47 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2k2fjsnlud2x2h6n
GET https://markdownregistry.com/api/v1/resolve?ref=vargasjr-dev/mycadet-temp/llm-cost-optimizer
GET https://markdownregistry.com/api/v1/blob/a564b7565e4c5563036280d9e3f4e4a6853a11e4898fc9796ecbe00cf1d13e3e

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 vargasjr-dev/mycadet-temp

AGENTS.md AGENTS.md file
vargasjr-dev/mycadet-temp · AGENTS.md
git:20261023.9cb946d · audit A · 47 stars
acp SKILL.md skill
vargasjr-dev/mycadet-temp · assistant/src/config/bundled-skills/acp/SKILL.md · Set up, authenticate, and run external coding agents (Claude Code, Codex) via the Agent Client Protocol
git:20261007.09b94d2 · audit A · 47 stars
app-builder SKILL.md skill
vargasjr-dev/mycadet-temp · assistant/src/config/bundled-skills/app-builder/SKILL.md · Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations…
git:20261007.09b94d2 · audit A · 47 stars
computer-use SKILL.md skill
vargasjr-dev/mycadet-temp · assistant/src/config/bundled-skills/computer-use/SKILL.md · Control a connected desktop
git:20261007.09b94d2 · audit A · 47 stars
contacts SKILL.md skill
vargasjr-dev/mycadet-temp · assistant/src/config/bundled-skills/contacts/SKILL.md · Manage contacts, communication channels, access control, and invite links
git:20261007.09b94d2 · audit A · 47 stars
conversation-groups SKILL.md skill
vargasjr-dev/mycadet-temp · assistant/src/config/bundled-skills/conversation-groups/SKILL.md · Organize conversations into custom sidebar groups — list groups, create new ones, and file conversations into them
git:20261007.09b94d2 · audit A · 47 stars
document-editor SKILL.md skill
vargasjr-dev/mycadet-temp · assistant/src/config/bundled-skills/document-editor/SKILL.md · Use whenever the user wants to write or draft an article, blog post, essay, report, or any long-form content. Creates…
git:20261007.09b94d2 · audit A · 47 stars
followups SKILL.md skill
vargasjr-dev/mycadet-temp · assistant/src/config/bundled-skills/followups/SKILL.md · Track sent messages awaiting responses across communication channels
git:20261007.09b94d2 · audit A · 47 stars
image-studio SKILL.md skill
vargasjr-dev/mycadet-temp · assistant/src/config/bundled-skills/image-studio/SKILL.md · Create images from a text description, or edit photos and graphics the user provides (remove backgrounds or watermarks…
git:20261007.09b94d2 · audit A · 47 stars
media-processing SKILL.md skill
vargasjr-dev/mycadet-temp · assistant/src/config/bundled-skills/media-processing/SKILL.md · Ingest and process media files (video, audio, image)
git:20261007.09b94d2 · audit A · 47 stars
messaging SKILL.md skill
vargasjr-dev/mycadet-temp · assistant/src/config/bundled-skills/messaging/SKILL.md · Read, search, send, and manage messages across Gmail, Outlook, Telegram, and other platforms
git:20261011.59db167 · audit A · 47 stars
phone-calls SKILL.md skill
vargasjr-dev/mycadet-temp · assistant/src/config/bundled-skills/phone-calls/SKILL.md · Make outgoing phone calls, receive incoming calls, and pull up past call transcripts
git:20261007.09b94d2 · audit A · 47 stars

Every file in vargasjr-dev/mycadet-temp

Other files named llm-cost-optimizer

llm-cost-optimizer SKILL.md skill
vellum-ai/vellum-assistant · skills/llm-cost-optimizer/SKILL.md · Analyze and reduce LLM spend: read usage breakdowns by call site, model, and inference profile, understand…
git:20260901.63b6d83 · audit A · 1,467 stars
llm-cost-optimizer SKILL.md skill
borghei/claude-skills · engineering/llm-cost-optimizer/SKILL.md · This skill should be used when the user asks to "estimate LLM costs", "count tokens in prompts", "optimize prompt token…
v1.1.0 · audit A · 1,019 stars

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