tokenwise

مسیریاب مدل سنجش‌محور برای Claude Code با ثبت هزینهٔ واقعی

TokenWise بر اساس نوع کار، Haiku، Sonnet یا Opus را انتخاب می‌کند، هزینهٔ واقعی هر کار را ثبت می‌کند و پیش از اتکا به صرفه‌جویی، رده‌های ارزان‌تر را A/B می‌آزماید.

چه چیزی می‌گیرید

  • دسته‌بندی کارها برای مسیریابی
  • ثبت هزینهٔ واقعی
  • آزمون A/B رده‌های ارزان

برای چه کاری خوب است

  • کاهش هزینهٔ Claude Code
  • تیم‌هایی با مصرف بالا

برای چه کاری نیست

  • استفادهٔ کم و پراکنده

دربارهٔ این اسکیل

TokenWise — Measurement-Driven Model Router

Overview

The upstream package advertises model-tier routing, local NDJSON usage logs and an A/B comparison command. Evaluate those capabilities only in an installed, reviewed revision with the user's authorized model budget and actual workload. Task difficulty, response-quality rubrics and reported costs remain estimates unless independently measured.

This entry describes the upstream workflow; it does not bundle its commands or measurement implementation. Verify the installed revision, supported models and actual routing behavior before relying on a report. A user's workload and billing plan determine whether routing reduces paid usage.

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

TierModelTask class
MechanicalHaiku 4.5file reads, grep, format, rename, simple edits, doc lookups
Scoped reasoningSonnet 4.6single-file refactor, scoped research, test writing
SynthesisOpus 4.7architecture 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

Upstream describes project-local logs at .tokenwise/log.ndjson. Inspect the installed revision and dependencies for log contents, redaction, retention and network behavior; this single-file catalog entry cannot establish zero telemetry. Model routing and A/B runs send task context to the selected provider. Exclude secrets and obtain authorization for additional provider usage; keep logs out of public commits.

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

  • Treat reported costs as estimates until reconciled with actual provider usage and current pricing; no billing-error bound is established by this catalog entry
  • A/B test mode costs extra tokens (one task × N tiers) — intentional one-time validation
  • Anthropic-only by design (use LiteLLM, OpenRouter, or Bifrost for cross-vendor)
  • Verify the selected model in actual execution evidence; do not assume a model parameter or an installer probe guarantees that a specific client build honored routing

Source

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

دانلود ZIP