token-wise
Pacote de plugins · vivek-cactus
token-wise é um pacote de plugins para ferramentas de programação com IA publicado por vivek-cactus. Marketplaces que lemos e que o listam: 1 (Claude Code: claude-plugins-community). Vimos pela primeira vez em 2026-10-12 e não registramos mudanças desde então. Conforme nossa passagem pelos marketplaces em 2026-10-12.
A Claude Code plugin that routes text-heavy tasks to the right Claude model — saving tokens without sacrificing quality. Why Planning, CLAUDE.md generation, README writing, and PRDs don't need Opus when you're just structuring content. token-wise intercepts these tasks and runs them on Sonnet or Haiku instead, switching back to your session model automatically when done.
- Marketplaces
- 1
- Onde roda
- Instala-se como pacote de plugins
- Maior número publicado
- 1 Estrelas (GitHub) · Claude Code: claude-plugins-community
- Visto pela primeira vez
- 2026-10-12
- Última mudança
- Nenhuma registrada
- Marca de verificação
- Sem marcação
Onde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Abrir o código no GitHub) | Listado | 7d2d736 | Forks (GitHub): 0 Estrelas (GitHub): 1 |
Sem marcação |
Cada número é do próprio marketplace e nunca é somado entre marketplaces. Um marketplace que não publica números não mostra nenhum: sem número não é zero.
O que pode fazer
Instala-se na ferramenta de IA como pacote de plugins; o que ele inicia está listado abaixo.
- Ferramentas que declara
- Não publicado
- Variáveis de ambiente que pede
- Não publicado
- Hooks que executa
- 1
O que o pacote contém
Conforme publicado em Claude Code: claude-plugins-community.
Skills: 12
claude-md-haikuclaude-md-opusclaude-md-sonnetplan-haikuplan-opusplan-sonnetprd-haikuprd-opusprd-sonnetreadme-haikureadme-opusreadme-sonnet
Hooks: 1
UserPromptSubmit
O que mudou
Nada mudou neste plugin desde que começamos a acompanhá-lo.
O editor
vivek-cactus · Repositório: github.com/vivek-cactus/token-wise
Plugins semelhantes
Produtos cujos próprios nomes, descrições, ferramentas e skills são os mais próximos deste pelo significado, em todos os marketplaces que lemos. A proximidade é ordenada apenas dentro desta lista.
- claude-perfectionistClaude Perfectionist audits your Claude Code instruction harness — CLAUDE.md, rules, hooks, settings, MCP config — and finds contradictions, missing verification, stale commands…
- leanPlan tasks with optimal model routing to minimize token usage. Breaks work into steps, assigns each the right model (Haiku/Sonnet/Opus), adds quality gates between stages…
- please-optimize-my-claudeOptimize your CLAUDE.md hierarchy — deduplicate content, detect misplacement, compress bloat, and visualize token usage across global/project/repo levels.
- prompt-enhancer-packAuto-enhances vague prompts into well-structured, context-aware prompts before Claude responds. Includes four skills: /enhance (general), /enhance-code (detects your tech stack…
- claude-handoffAuto-generate handoff prompts and restart Claude Code with fresh context
- prompt-improverIntelligent prompt optimization using skill-based architecture. Enriches vague prompts with research-based clarifying questions before Claude Code executes them
- token-inspectorTwo skills that help you understand and optimize your Claude Code context window. Inspect Context gives you a full token breakdown by source (files, history, skills, MCP configs…
- dominion-flowResearch-backed orchestration for Claude Code. Structured workflow from idea to production with parallel execution, session memory, 70-point validation, autonomous mode, and…
- orchestratorGenerate ready-to-paste Claude Code prompts with the right agent, orchestration pattern, and safety rails. Orchestrator synthesises patterns from 6 open-source projects into a…
- brand-voice io.github.zoharbabin/brand-voiceEnforce brand writing guidelines in Claude Code — PostToolUse hook + MCP server
Plugins semelhantes por marketplace
A mesma pergunta feita a cada marketplace separadamente: existe lá um equivalente deste plugin?
Listado em Claude Code: claude-plugins-community (5)
- claude-perfectionistClaude Perfectionist audits your Claude Code instruction harness — CLAUDE.md, rules, hooks, settings, MCP config — and finds contradictions, missing verification, stale commands…
- leanPlan tasks with optimal model routing to minimize token usage. Breaks work into steps, assigns each the right model (Haiku/Sonnet/Opus), adds quality gates between stages…
- please-optimize-my-claudeOptimize your CLAUDE.md hierarchy — deduplicate content, detect misplacement, compress bloat, and visualize token usage across global/project/repo levels.
- prompt-enhancer-packAuto-enhances vague prompts into well-structured, context-aware prompts before Claude responds. Includes four skills: /enhance (general), /enhance-code (detects your tech stack…
- claude-handoffAuto-generate handoff prompts and restart Claude Code with fresh context
Listado em Claude Code: claude-plugins-official (5)
- outputaiOutput.ai workflow development toolkit for Claude Code. Adds 5 specialist agents (planner, builder, debugger, prompt writer, quality reviewer), 40+ slash-command skills covering…
- claude-md-managementTools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
- session-reportGenerate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects…
- ralph-loopInteractive self-referential AI loops for iterative development, implementing the Ralph Wiggum technique. Claude works on the same task repeatedly, seeing its previous work, until…
- atomic-agentsComprehensive development workflow for building AI agents with the Atomic Agents framework. Includes specialized agents for schema design, architecture planning, code review, and…
Listado em Claude: knowledge-work-plugins (5)
- AI-FirstifyAI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
- QodoBring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
- mintlifyBuild beautiful documentation sites with Mintlify. Convert non-markdown files into properly formatted MDX pages, add and modify content with correct component use, and automate…
- sanitySanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual…
- langfuseSkills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Listado em Codex: openai-curated (openai/plugins) (5)
- Plugin EvalEvaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
- OpenAI DevelopersBuild with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
- CodeRabbitAI-powered code review in Codex, powered by CodeRabbit.
- FigmaFigma workflows for design implementation, Code Connect templates, and design system rule generation.
- GitHubInspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
Listado em Community GitHub marketplaces (5)
- magentsShared session bus so Cursor can hand off with Claude, Codex, Grok, and friends.
- Endor Labs Agent KitEndor Labs workflow agents and setup for Claude Code.
- atomic-agentsComprehensive development workflow for building AI agents with the Atomic Agents framework. Includes specialized agents for schema design, architecture planning, code review, and…
- WaggleLocal graph memory that lets Codex recall project context across sessions.
- Dash0 ObservabilityOpenTelemetry observability for OpenAI Codex sessions. Captures prompts, tool calls, MCP calls, sub-agent activity, and token usage as OTel traces.
Listado em Copilot CLI: github/awesome-copilot (5)
- noob-modePlain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, jargon-free English with…
- ai-team-orchestrationRun a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
- edge-ai-tasksTask Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
- copilot-goal-skillGoal-driven task orchestration with independent verification. Interviews the user to define a clear goal, then loops between a Builder subagent (does the work) and an Inspector…
- ai-readyAnalyze any repository and generate AI-ready configuration — AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more. Mines your PR review patterns and creates…
Listado em Copilot CLI: github/copilot-plugins (5)
- microsoft-365-agents-toolkitToolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
- azure-devops-copilot-pluginBring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
- advanced-securityAdvanced Security plugin for GitHub Copilot.
- workiqQuery Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
- workiq-productivityWorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
Listado em Cursor: cursor/plugins (5)
- GammaGenerate presentations, documents, and webpages.
- AdvisorConsult a stronger model before major decisions, when stuck, and before declaring done.
- Ralph LoopIterative self-referential AI loops using the Ralph Wiggum technique.
- Origin AppsSkills for building on the Cursor Origin API. Fetch the live spec first, then follow the Origin rules for credentials, scopes, webhooks, paging, and errors. Includes a skill that…
- Cursor SDKBuild apps, scripts, and automations with the TypeScript SDK.
Listado em Docker MCP Catalog (5)
- Sequa.AIStop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
- ZenBridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
- Desktop CommanderMCP server for terminal commands, file operations, and process management
- Gemini API DocsProvides tools to search and retrieve Google Gemini API documentation.
- GlifGenerate images, video, and audio with Glif's media-generation agent
Listado em Official MCP Registry (5)
- brand-voice io.github.zoharbabin/brand-voiceEnforce brand writing guidelines in Claude Code — PostToolUse hook + MCP server
- LLM CLI GatewayOne MCP endpoint for Claude Code, Codex, Gemini, Grok and Mistral CLIs, with durable async jobs.
- Promptlint MCPStatic linter for AI prompts: contradictions, redundancy, ambiguity, and fluff.
- AI UsageReports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
- thread-keeperMulti-agent shared brain across Claude, Codex, Antigravity, Gemini, Copilot, and VS Code.
Encontrados pelo significado, não por código ou repositório em comum: plugins semelhantes continuam sendo produtos distintos, e isto não é uma avaliação nem uma recomendação.
Este plugin é seu?
Comprove que você mantém o plugin com um arquivo no repositório, um arquivo no seu domínio ou um registro DNS. Você recebe alertas quando um marketplace o publica, o remove, muda o selo de verificado ou o que ele pede, e pode colocar o endpoint remoto em monitoramento como serviço web.
Dados de Claude Code: claude-plugins-community. Os números vêm das nossas próprias passagens regulares pelos marketplaces, última leitura em . Não publicamos dados de contato dos editores de plugins.