S Skillteca
Receber por email
Explorar Categorias Coleções Newsletter
← Voltar para o catálogo

tokenwise

Desenvolvimento Autor: sickn33

Measurement-driven model router for Claude Code. Routes Haiku/Sonnet/Opus per task class, logs every routed task with real $ numbers, and A/B tests cheaper tiers before you trust the savings.

41.2kestrelas
Atualizado há 4 meses
Ver no GitHub ↗ Licença: MIT

Como adicionar

/plugin marketplace add sickn33/antigravity-awesome-skills

O comando exato pode variar conforme o repositório. Confira o README no GitHub.

Para o autor da skill

Cole no README do seu repo

Mostra que sua skill está catalogada na Skillteca, gera backlink e tráfego rastreável.

[![Skillteca](https://www.skillteca.com.br/api/badge/tokenwise-sickn33/svg)](https://www.skillteca.com.br/skills/tokenwise-sickn33)
#ai #git #github #test

Skills relacionadas

Ver todas de Desenvolvimento →

claude-api

153.1k

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a C

Desenvolvimento #ai #api por anthropics

skill-creator

153.1k

Crie novas skills, modifique e aprimore as existentes, e meça seu desempenho. Utilize para desenvolver, editar, otimizar, testar e comparar skills, além de refinar suas descrições para maior precisão de acionamento.

Desenvolvimento #test por anthropics

claude-code-plugin-release

83.4k

Fluxo de trabalho automatizado de versionamento semântico e lançamento para plugins do Claude Code. Gerencia incrementos de versão em manifestos package.json, marketplace.json, plugin.json, publicação npm (para que npx claude-mem@X.Y.Z seja resolvido), verificação de build, marcação git, lançamentos no GitHub e geração de changelog.

Desenvolvimento #ai #git por thedotmack

claude-mem

83.4k

Contexto Persistente Entre Sessões para Cada Agente – Captura tudo o que seu agente faz durante as sessões, comprime com IA e injeta contexto relevante de volta em sessões futuras. Compatível com Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode e mais.

Desenvolvimento #ai por thedotmack

Alerta por categoria

Receba novas skills de Desenvolvimento toda segunda

1 email curto, só com as skills novas de Desenvolvimento. 4 minutos de leitura, sem spam, cancela com 1 clique.

Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.

Ler descrição completa

TokenWise — Measurement-Driven Model Router

Overview

A Claude Code skill that auto-routes subtasks to the cheapest model that can handle them (Haiku for grunt work, Sonnet for scoped reasoning, Opus only for synthesis), then logs every routed task to a local NDJSON with real token + cost numbers. Includes an A/B test subcommand that runs the same task across multiple tiers and scores quality, so the routing decisions are verified against the user's real workload — not estimated.

Anthropic's own bug tracker (Issue #27665) reports 93.8% of Max-subscriber Claude Code tokens flow to Opus. Existing routers (claude-router, wshobson, VoltAgent) either pin models statically or route by vibes-based heuristics with no measurement. TokenWise fills the measurement gap.

When to use

  • Cutting Claude Code token spend without sacrificing output quality
  • Validating whether Haiku/Sonnet is "good enough" for a specific task class before trusting auto-routing
  • Auditing where Opus tokens are actually being burned
  • Logging per-session cost data for finance or chargeback

Subcommands

  • /tokenwise:install — guided installer with diff preview, automatic backups, and --dry-run mode
  • /tokenwise:report — per-session token + cost summary vs all-Opus baseline
  • /tokenwise:summary [--week|--month|--all] — historical aggregate with trend
  • /tokenwise:ab "<task>" — A/B test the same task at multiple tiers, generates a markdown comparison
  • /tokenwise:undo — restore CLAUDE.md / settings.json from backup

Routing taxonomy

| Tier | Model | Task class | |---|---|---| | Mechanical | Haiku 4.5 | file reads, grep, format, rename, simple edits, doc lookups | | Scoped reasoning | Sonnet 4.6 | single-file refactor, scoped research, test writing | | Synthesis | Opus 4.7 | architecture decisions, multi-file refactor, security review |

Safety caps:

  • Haiku never spawns further subagents
  • Max spawn depth = 2
  • Subagents that need a smarter model return to parent — they never escalate on their own
  • Tasks under 100 chars with no file context run inline (subagent overhead > savings)
  • Subagent context >30k tokens bumps a tier

Privacy

Zero telemetry. All logs in .tokenwise/log.ndjson local to the project. Task descriptions truncated to 80 chars and stripped of file contents before logging. No analytics endpoint exists in the source.

Install

In any Claude Code session:

/plugin marketplace add CodeShuX/tokenwise
/plugin install tokenwise@tokenwise

Then run /tokenwise:install and follow the guided prompts.

Limitations

  • Token counts approximate to ±2% vs Anthropic billing
  • A/B test mode costs extra tokens (one task × N tiers) — intentional one-time validation
  • Anthropic-only by design (use LiteLLM or OpenRouter for cross-vendor)
  • Subagent model: param has known silent-fail bugs on some Claude Code builds — skill probes for this at install and refuses to configure if routing is broken

Source

  • Repo: https://github.com/CodeShuX/tokenwise
  • License: MIT
  • Author: CodeShuX
Compartilhar X LinkedIn