add-model-price
por langfuse
Úsalo al editar worker/src/constants/default-model-prices.json, packages/shared/src/server/llm/types.ts, niveles de precios, IDs de tokenizador o expresiones regulares matchPattern…
npx skills add https://github.com/langfuse/langfuse --skill add-model-priceAdd Model Price
Use this skill for model pricing changes in worker/ and shared LLM type
updates in packages/shared/.
When to Apply
- Editing
worker/src/constants/default-model-prices.json - Editing
packages/shared/src/server/llm/types.ts - Adding a new priced model
- Updating provider prices, cache pricing, or tier conditions
- Expanding regex coverage for Bedrock, Vertex, Azure, or provider-prefixed model names
- Auditing default model prices for stale, missing, or unmatched provider pricing
How to Read This Skill
- Use this
SKILL.mdas the high-level workflow and helper index. - Open only the specific reference file that matches the task.
Quick Start Checklist
Adding a New Model
- Gather official pricing from the provider documentation.
- Generate a lowercase UUID for the model entry.
- Create a
matchPatternthat covers supported provider formats. - Add at least one default pricing tier.
- Insert the pricing entry into
worker/src/constants/default-model-prices.json. - Update
packages/shared/src/server/llm/types.tsif the model should be selectable in playground or evaluation flows. - Validate the JSON after editing.
Updating an Existing Model
- Update the relevant prices, keys, tiers, or regexes.
- Refresh
updatedAtto today's ISO-8601 timestamp. - Validate the JSON after editing.
Reference Map
| Topic | Read this when | File |
|---|---|---|
| Schema and tier rules | You need the entry shape or pricing-tier invariants | references/schema-and-tiers.md |
| Provider sources and price keys | You need official pricing URLs, per-token conversion, or provider-specific usage keys | references/provider-sources-and-price-keys.md |
| Match patterns | You are editing matchPattern regexes or provider coverage | references/match-patterns.md |
| Workflow and validation | You are applying the end-to-end edit process or checking common mistakes | references/workflow-and-validation.md |
| Automated audit mode | You are running a scheduled/default-price audit and need CI-safe edit rules | references/automated-audit.md |
Deterministic Helpers
- Pricing file validator:
node .agents/skills/add-model-price/scripts/validate-pricing-file.mjs - Match-pattern tester:
node .agents/skills/add-model-price/scripts/test-match-pattern.mjs --model <modelName> --accept <sample...> --reject <sample...> - Direct regex tester:
node .agents/skills/add-model-price/scripts/test-match-pattern.mjs --pattern '(?i)^(openai/)?(gpt-4o)$' --accept gpt-4o openai/gpt-4o --reject gpt-4o-mini
Más skills de langfuse
agent-setup-maintenance
langfuse
Usa esta habilidad al cambiar la configuración del agente compartido para el repositorio.
official
backend-dev-guidelines
langfuse
Guía compartida de backend para el monorepo de Langfuse con Next.js, tRPC, BullMQ y TypeScript. Úsala al crear o revisar routers de tRPC, endpoints REST públicos, BullMQ…
official
changelog-writing
langfuse
Usa esta habilidad cuando una rama de funcionalidad completada necesite una entrada en el registro de cambios.
official
clickhouse-best-practices
langfuse
DEBE USARSE al revisar esquemas, consultas o configuraciones de ClickHouse. Contiene 28 reglas que DEBEN verificarse antes de proporcionar recomendaciones. Siempre leer…
official
code-review
langfuse
Usa esta habilidad cuando la tarea sea revisar cambios de código en lugar de implementar una funcionalidad.
official
frontend-browser-review
langfuse
Usa esta habilidad cuando un cambio afecte lo que los usuarios ven o hacen en el navegador.
official
skill-developer
langfuse
Crear y gestionar habilidades de Claude Code siguiendo las mejores prácticas de Anthropic. Usar al crear nuevas habilidades, modificar skill-rules.json, entender desencadenadores…
official
turborepo
langfuse
Sistema de construcción para monorepos de JavaScript/TypeScript. Turborepo almacena en caché las salidas de las tareas y ejecuta tareas en paralelo basándose en el grafo de dependencias.
official