[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78FME51R14E8YFNEBAM95DB":3,"skill-same:01M78FME51R14E8YFNEBAM95DB":68},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M78FME51R14E8YFNEBAM95DB","tokenwise",null,"Measurement-driven model router for Claude Code. Routes Haiku\u002FSonnet\u002FOpus per task class, logs every routed task with real $ numbers, and A\u002FB tests cheaper tiers before you trust the savings.","princepatel04477-web\u002Ftrivoxa-group","princepatel04477-web","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F227740714?v=4","01M788ZAJ2KECD5KXVP55PZXKS","Prince Patel","01M788ZAJTCN8YSD737MRSKC5Q",0,"MIT","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Ftokenwise\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tokenwise\ndescription: \"Measurement-driven model router for Claude Code. Routes Haiku\u002FSonnet\u002FOpus per task class, logs every routed task with real $ numbers, and A\u002FB tests cheaper tiers before you trust the savings.\"\ncategory: developer-tools\nrisk: critical\nsource: community\nsource_repo: CodeShuX\u002Ftokenwise\nsource_type: community\ndate_added: \"2026-05-12\"\nauthor: CodeShuX\ntags: [model-routing, token-optimization, cost-reduction, anthropic, haiku, sonnet, opus, claude-code, ab-testing, measurement]\ntools: [claude]\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002FCodeShuX\u002Ftokenwise\u002Fblob\u002Fmain\u002FLICENSE\"\nplugin:\n  targets:\n    codex: blocked\n    claude: blocked\n---\n\n# TokenWise — Measurement-Driven Model Router\n\n## Overview\n\nA 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\u002FB 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.\n\nAnthropic'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.\n\n## When to use\n\n- Cutting Claude Code token spend without sacrificing output quality\n- Validating whether Haiku\u002FSonnet is \"good enough\" for a specific task class before trusting auto-routing\n- Auditing where Opus tokens are actually being burned\n- Logging per-session cost data for finance or chargeback\n\n## Subcommands\n\n- `\u002Ftokenwise:install` — guided installer with diff preview, automatic backups, and `--dry-run` mode\n- `\u002Ftokenwise:report` — per-session token + cost summary vs all-Opus baseline\n- `\u002Ftokenwise:summary [--week|--month|--all]` — historical aggregate with trend\n- `\u002Ftokenwise:ab \"\u003Ctask>\"` — A\u002FB test the same task at multiple tiers, generates a markdown comparison\n- `\u002Ftokenwise:undo` — restore CLAUDE.md \u002F settings.json from backup\n\n## Routing taxonomy\n\n| Tier | Model | Task class |\n|---|---|---|\n| Mechanical | Haiku 4.5 | file reads, grep, format, rename, simple edits, doc lookups |\n| Scoped reasoning | Sonnet 4.6 | single-file refactor, scoped research, test writing |\n| Synthesis | Opus 4.7 | architecture decisions, multi-file refactor, security review |\n\nSafety caps:\n- Haiku never spawns further subagents\n- Max spawn depth = 2\n- Subagents that need a smarter model return to parent — they never escalate on their own\n- Tasks under 100 chars with no file context run inline (subagent overhead > savings)\n- Subagent context >30k tokens bumps a tier\n\n## Privacy\n\nZero telemetry. All logs in `.tokenwise\u002Flog.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.\n\n## Install\n\nIn any Claude Code session:\n\n```\n\u002Fplugin marketplace add CodeShuX\u002Ftokenwise\n\u002Fplugin install tokenwise@tokenwise\n```\n\nThen run `\u002Ftokenwise:install` and follow the guided prompts.\n\n## Limitations\n\n- Token counts approximate to ±2% vs Anthropic billing\n- A\u002FB test mode costs extra tokens (one task × N tiers) — intentional one-time validation\n- Anthropic-only by design (use LiteLLM or OpenRouter for cross-vendor)\n- 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\n\n## Source\n\n- Repo: https:\u002F\u002Fgithub.com\u002FCodeShuX\u002Ftokenwise\n- License: MIT\n- Author: CodeShuX\n","# TokenWise — Measurement-Driven Model Router\n\n## Overview\n\nA 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\u002FB 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.\n\nAnthropic'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.\n\n## When to use\n\n- Cutting Claude Code token spend without sacrificing output quality\n- Validating whether Haiku\u002FSonnet is \"good enough\" for a specific task class before trusting auto-routing\n- Auditing where Opus tokens are actually being burned\n- Logging per-session cost data for finance or chargeback\n\n## Subcommands\n\n- `\u002Ftokenwise:install` — guided installer with diff preview, automatic backups, and `--dry-run` mode\n- `\u002Ftokenwise:report` — per-session token + cost summary vs all-Opus baseline\n- `\u002Ftokenwise:summary [--week|--month|--all]` — historical aggregate with trend\n- `\u002Ftokenwise:ab \"\u003Ctask>\"` — A\u002FB test the same task at multiple tiers, generates a markdown comparison\n- `\u002Ftokenwise:undo` — restore CLAUDE.md \u002F settings.json from backup\n\n## Routing taxonomy\n\n| Tier | Model | Task class |\n|---|---|---|\n| Mechanical | Haiku 4.5 | file reads, grep, format, rename, simple edits, doc lookups |\n| Scoped reasoning | Sonnet 4.6 | single-file refactor, scoped research, test writing |\n| Synthesis | Opus 4.7 | architecture decisions, multi-file refactor, security review |\n\nSafety caps:\n- Haiku never spawns further subagents\n- Max spawn depth = 2\n- Subagents that need a smarter model return to parent — they never escalate on their own\n- Tasks under 100 chars with no file context run inline (subagent overhead > savings)\n- Subagent context >30k tokens bumps a tier\n\n## Privacy\n\nZero telemetry. All logs in `.tokenwise\u002Flog.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.\n\n## Install\n\nIn any Claude Code session:\n\n```\n\u002Fplugin marketplace add CodeShuX\u002Ftokenwise\n\u002Fplugin install tokenwise@tokenwise\n```\n\nThen run `\u002Ftokenwise:install` and follow the guided prompts.\n\n## Limitations\n\n- Token counts approximate to ±2% vs Anthropic billing\n- A\u002FB test mode costs extra tokens (one task × N tiers) — intentional one-time validation\n- Anthropic-only by design (use LiteLLM or OpenRouter for cross-vendor)\n- 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\n\n## Source\n\n- Repo: https:\u002F\u002Fgithub.com\u002FCodeShuX\u002Ftokenwise\n- License: MIT\n- Author: CodeShuX\n",{"name":5,"risk":24,"tags":25,"tools":36,"author":38,"plugin":39,"source":42,"license":15,"category":43,"date_added":44,"description":7,"source_repo":45,"source_type":42,"license_source":46},"critical",[26,27,28,29,30,31,32,33,34,35],"model-routing","token-optimization","cost-reduction","anthropic","haiku","sonnet","opus","claude-code","ab-testing","measurement",[37],"claude","CodeShuX",{"targets":40},{"codex":41,"claude":41},"blocked","community","developer-tools","2026-05-12","CodeShuX\u002Ftokenwise","https:\u002F\u002Fgithub.com\u002FCodeShuX\u002Ftokenwise\u002Fblob\u002Fmain\u002FLICENSE","master","877653a671c51fae6476bd9f0d34ee6c408d68b9",".github\u002Fskills\u002Ftokenwise","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group","https:\u002F\u002Ftrivoxa-group.vercel.app","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web","2026-08-01 17:29:31",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add princepatel04477-web\u002Ftrivoxa-group --skill tokenwise",{"tool":60,"command":61},"bunx","bunx skills add princepatel04477-web\u002Ftrivoxa-group --skill tokenwise",{"tool":63,"command":64},"pnpm","pnpm dlx skills add princepatel04477-web\u002Ftrivoxa-group --skill tokenwise","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Ftokenwise\u002FSKILL.md",true,[],[69,76,83,90,97,104],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M78G4Z5RFJ72G536XYPC77PG","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M78G4WQMHRST36KDP7AV3NR3","zoom-automation","Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzoom-automation\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M78G4T37F4SPS7M4KT0A8JJB","zoho-crm-automation","Automate Zoho CRM tasks via Rube MCP (Composio): create\u002Fupdate records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzoho-crm-automation\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M78G4QAJMF71KD1G38MNDQYK","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M78G4MS3WE96MH5P561KFY95","zipai-optimizer","Adaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware, MCP-aware.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzipai-optimizer\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M78G4GZ0T47C6929V9CVH1AK","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[]]