Skip to content
Agentmart
Submit a tool

cost-aware-llm

Patrones para controlar costos de API de LLMs.

Skill by webcomunicasolutions

IndexedMIT
Write a review

Chalk Labs

Need help deploying cost-aware-llm?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/webcomunicasolutions-cost-aware-llm

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Patrones para controlar costos de API de LLMs. Model routing, budget tracking, prompt caching, retry inteligente. Usar cuando se construyan pipelines de IA o se optimicen costos.

Use cases: backend, ml, finance, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/cost-aware-llm

What's inside

Skill name
cost-aware-llm
Description
Patrones para controlar costos de API de LLMs. Model routing, budget tracking, prompt caching, retry inteligente. Usar cuando se construyan pipelines de IA o se optimicen costos.
License
MIT
Instructions
51 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Cost-Aware LLM Pipeline

## Selección inteligente de modelo
| Tarea | Modelo | Costo relativo |
|-------|--------|---------------|
| Clasificación, formateo | Haiku | 1x |
| Implementación general | Sonnet | 4x |
| Arquitectura, investigación | Opus | 15x |

Regla: empieza con el modelo más barato que pueda hacer el trabajo. Escala solo si la calidad no es suficiente.

## Budget tracking inmutable
```python
@dataclass(frozen=True)
class CostTracker:
    total_cost: float
    total_tokens: int
    calls: int

    def with_call(self, cost: float, tokens: int) -> 'CostTracker':
        return CostTracker(
            total_cost=self.total_cost + cost,
            total_tokens=self.total_tokens + tokens,
            calls=self.calls + 1
        )
```
- Nunca mutar estado - sin acumulación oculta de costos
- Set budget limits ANTES de procesar batches

## Retry inteligente
- Retry SOLO errores transitorios: network, rate limits, 5xx
- Fail fast en permanentes: auth errors, malformed requests, 4xx
- Exponential backoff: 1s, 2s, 4s, 8s, máximo 3 reintentos

## Prompt caching
- System prompts largos - cachear server-side
- Reduce latencia y costos de tokens
- Implementar en: Anthropic (cache_control), OpenAI (cached prompts)

## Observabilidad
- Log CADA llamada: modelo, tokens in/out, costo, latencia
- Dashboard de gasto acumulado
- Alertas cuando se acerca al budget

## Principios
- Security de datos > minimización ciega de costos
- Batch processing cuando sea posible (menor overhead)
- Evaluar calidad vs costo periódicamente
- No usar Opus para tareas que Sonnet hace bien

From webcomunicasolutions/claude-code-toolkit, MIT.

More from webcomunicasolutions/claude-code-toolkit

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Mar 24, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from webcomunicasolutions

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get cost-aware-llm running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying cost-aware-llm?

CallGet help
Cite this page

cost-aware-llm skill. Agent Mart. https://agentmart.dev/skills/webcomunicasolutions-cost-aware-llm (last updated 2026-10-24)