Home / ulises-jeremias / agent-toolkit · plugins/agent-toolkit-complete/.github/skills/llm-cost-advisor/SKILL.md · GitHub

llm-cost-advisor skillA

llm-cost-advisor is agent-read markdown (skill) from ulises-jeremias/agent-toolkit: WHAT — Recommend the most cost-effective LLM provider for a given task type. Shows estimated.

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.

What the file says

# LLM Cost Advisor (WHAT)

Recommend the right provider for the task at hand — balancing quality, cost, and privacy.

## When to use

- User asks "which model should I use for X?"
- Before scheduling expensive loops (pr-babysitter, ci-sweeper)
- When dev-companion jobs are unexpectedly expensive
- When choosing between local and cloud providers for sensitive work

## Out of scope

- Does NOT configure providers — that's done via env vars and `loadenv`
- Does NOT run LLM calls — it advises, the runner executes

## Workflow

**Step 1 — Check available providers:**

```bash
devcompanion llm-status
```

**Step 2 — Classify the task:**

| Task type | Recommended tier | Why |
|-----------|-----------------|-----|
| Interactive code review, planning, debugging | Claude Sonnet / GPT-4o | Reasoning quality matters |
| Batch labeling, summarization, triage | Claude Haiku / GPT-4o-mini | High volume, lower stakes |
| Private/sensitive codebase work | Ollama or OpenCode | Stays local, zero cost |
| Loop L1 (observation only) | Haiku / GPT-4o-mini | Low stakes, runs daily |
| Loop L2 (PR creation) | Sonnet | Creates external artifacts |
…

Read the whole file at its exact version.

How to install

Latest version
mdr add ulises-jeremias/agent-toolkit/llm-cost-advisor@v1.0
Exact content
mdr add ulises-jeremias/agent-toolkit/llm-cost-advisor@sha256:a2618beaa3167940

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_vjqb4g5sxjbo6lhh.svg)](https://markdownregistry.com/a/art_vjqb4g5sxjbo6lhh)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v1.0 latest2026-08-31 856ee57 2,937 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 (2937 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

ulises-jeremias/agent-toolkit · 18 stars · license MIT · pushed 2026-09-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vjqb4g5sxjbo6lhh
GET https://markdownregistry.com/api/v1/resolve?ref=ulises-jeremias/agent-toolkit/llm-cost-advisor
GET https://markdownregistry.com/api/v1/blob/a2618beaa31679402c893c02342d7a1f49086d567464394b1f58dbc15df955f7

Your agent 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.

More from ulises-jeremias/agent-toolkit

AGENTS.md agents
ulises-jeremias/agent-toolkit · AGENTS.md
git:20260913.6bf289b · audit A · 18 stars
DESIGN.md@docs/desktop design
ulises-jeremias/agent-toolkit · docs/desktop/DESIGN.md
git:20260913.6bf289b · audit A · 18 stars
AGENTS.md@plugins/agent-toolkit-agents agents
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-agents/AGENTS.md
git:20260831.856ee57 · audit A · 18 stars
adr skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/adr/SKILL.md · WHAT — Create and maintain Architecture Decision Records (ADRs) per the process. Covers when
git:20260901.5d17d6a · audit A · 18 stars
agreement skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/agreement/SKILL.md · WHAT - Capture explicit agreements, terms, parties involved, dates, validity, and linked
git:20260831.856ee57 · audit A · 18 stars
architecture-diagram skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/architecture-diagram/SKILL.md · WHAT — Create polished dark-themed architecture diagrams as self-contained HTML+SVG files (inline SVG, CSS styling…
v1.0.0 · audit B · 18 stars
assistant skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/assistant/SKILL.md · Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs
v2.1 · audit A · 18 stars
aws-well-architected-review skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/aws-well-architected-review/SKILL.md · WHAT — AWS Well-Architected Framework review (6 pillars) — operational excellence, security, reliability, performance…
v1.0 · audit A · 18 stars
blast-radius skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/blast-radius/SKILL.md · Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe…
git:20260831.856ee57 · audit A · 18 stars
bug skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/bug/SKILL.md · WHAT - Draft and review bugs using the Bug Template; classifies whether an issue should be
git:20260831.856ee57 · audit A · 18 stars
c4-model skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/c4-model/SKILL.md · WHAT — C4 model methodology (Context, Container, Component, Code) guidance — what to draw at each level, when, and how…
v1.0 · audit A · 18 stars
chrome-devtools skill
ulises-jeremias/agent-toolkit · plugins/agent-toolkit-complete/.github/skills/chrome-devtools/SKILL.md · Use Chrome DevTools MCP to control and inspect a live Chrome instance for network, console, performance, rendering, and…
git:20260831.856ee57 · audit B · 18 stars

Every file in ulises-jeremias/agent-toolkit

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