model-right-sizer
Model-selection economist agent for Claude Code: decides which Claude model (and effort/token budget) each task in a flow should run on by weighing effectiveness need against…
Plugin-Paket · von CloudZero, Inc.
Überblick
model-right-sizer ist ein Plugin-Paket für KI-Coding-Tools von CloudZero, Inc.. Marktplätze, die wir lesen und die es listen: 1 (Community GitHub marketplaces). Wir haben es erstmals am 2026-10-15 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-22.
Model-selection economist agent for Claude Code: decides which Claude model (and effort/token budget) each task in a flow should run on by weighing effectiveness need against efficiency pressure and difficulty, bookended around a build as a right-sizing blueprint and a closing usage report -- with token_ceiling itself computed deterministically from six rated real-work signals, not free-handed. Ships with eleven companion skills: installing the standing before/after mandate in a target repo, previewing the routing map for an intent without building anything, retroactively auditing every real model call already shipped in a target repo, prescribing a minimal output schema for one agent's handoff to its controller, guarding token budgets and the routing-map status ledger while work is in flight, validating candidate real-work signals and studying/tuning the agent's research-grounded layers, and publishing dated release/research reports.
Was es abfragt
- Wird als Plugin-Paket installiert
Keiner der Marktplätze, die wir lesen, veröffentlicht seine Tools oder die abgefragten Einstellungen.
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als Claude-Code-Plugin
Erstellt aus den Angaben von Community GitHub marketplaces.
/plugin marketplace add cloudzero/cloudzero-claude-marketplace
/plugin install model-right-sizer@cloudzeroWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Community-Marktplatz cloudzero/cloudzero-claude-marketplace (Quelle auf GitHub öffnen) | Gelistet | 0.2.0 | Forks (GitHub): 8 Sterne (GitHub): 25 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
In einem Community-Marktplatz gelistet
| Marktplatz | Repository | Sterne (GitHub) |
|---|---|---|
| cloudzero | cloudzero/cloudzero-claude-marketplace | 25 |
Was das Paket enthält
So veröffentlicht auf Community GitHub marketplaces.
Skills: 11
model-right-sizer-auditmodel-right-sizer-budget-guardmodel-right-sizer-dryrunmodel-right-sizer-holdout-tuningmodel-right-sizer-installmodel-right-sizer-layer-ablationmodel-right-sizer-prompt-tuningmodel-right-sizer-release-reportmodel-right-sizer-research-reportmodel-right-sizer-schemamodel-right-sizer-signal-validation
Agenten: 1
model-right-sizer
Was sich geändert hat
- Wird seitdem als Produkt geführt
- Community GitHub marketplaces: erschienen
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
See what Claude costs you and spend less of it. In chat: hand a long chat over to a new one, digest long documents, set up Projects, check tokens, sharpen prompts. In Claude Code…
-
Audit and optimize Claude Code context window usage. Runs a 9-phase analysis covering plugins, hooks, CLAUDE.md cascade, MCP servers, environment settings, zombie process…
-
Cut LLM API spend via model routing, prompt caching, prompt compression, and per-feature cost observability. Use when AI costs are too high, choosing between models, or launching…
-
Install and maintain a "model routing" section in a project's CLAUDE.md that teaches Claude Code which model to use for which work, including delegating to GPT models via the…
-
Context engineering plugin for Claude Code — real-time prompt scoring, RLM adaptive weights, and token optimization. Scores every tool use across 5 dimensions (token utilization…
-
Produces evidence-based model routing plans: maps each task unit to the best-suited AI model (Claude, GPT, Gemini, open-weight) using a 30-category task taxonomy, decision rules…
-
Claude Code efficiency and hygiene toolkit. Surfaces token spend across the 5h / 7d / Sonnet-7d billing windows with per-model / per-agent / per-skill attribution, and audits your…
-
Research-backed orchestration for Claude Code. Structured workflow from idea to production with parallel execution, session memory, 70-point validation, autonomous mode, and…
-
Claude Code is great, but treating every prompt with full context is too expensive. I built Claude_Meister as an MCP plugin to dynamically route tasks and score memory, dropping…
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
Audit and optimize Claude Code context window usage. Runs a 9-phase analysis covering plugins, hooks, CLAUDE.md cascade, MCP servers, environment settings, zombie process…
-
Context engineering plugin for Claude Code — real-time prompt scoring, RLM adaptive weights, and token optimization. Scores every tool use across 5 dimensions (token utilization…
-
Research-backed orchestration for Claude Code. Structured workflow from idea to production with parallel execution, session memory, 70-point validation, autonomous mode, and…
-
Claude Code is great, but treating every prompt with full context is too expensive. I built Claude_Meister as an MCP plugin to dynamically route tasks and score memory, dropping…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Development kit for working with the Claude Agent SDK
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Langfuse observability plugin for Claude Code — captures and exports traces, spans, and session telemetry from Claude Code to Langfuse for LLM monitoring, debugging, and evaluation
-
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
-
Output.ai workflow development toolkit for Claude Code. Adds 5 specialist agents (planner, builder, debugger, prompt writer, quality reviewer), 40+ slash-command skills covering…
Gelistet auf Claude: knowledge-work-plugins (5)
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
Sanity 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…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search…
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
-
Answer product and business questions with data
Gelistet auf Community GitHub marketplaces (5)
-
See what Claude costs you and spend less of it. In chat: hand a long chat over to a new one, digest long documents, set up Projects, check tokens, sharpen prompts. In Claude Code…
-
Cut LLM API spend via model routing, prompt caching, prompt compression, and per-feature cost observability. Use when AI costs are too high, choosing between models, or launching…
-
Install and maintain a "model routing" section in a project's CLAUDE.md that teaches Claude Code which model to use for which work, including delegating to GPT models via the…
-
Produces evidence-based model routing plans: maps each task unit to the best-suited AI model (Claude, GPT, Gemini, open-weight) using a 30-category task taxonomy, decision rules…
-
Claude Code efficiency and hygiene toolkit. Surfaces token spend across the 5h / 7d / Sonnet-7d billing windows with per-model / per-agent / per-skill attribution, and audits your…
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Goal-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…
-
Plain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, jargon-free English with…
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
-
Skills and interactive Copilot canvas for designing, configuring, testing and deploying agents to Microsoft Foundry.
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
Build and manage Microsoft Dataverse solutions using natural language. Includes table/column creation, solution lifecycle, data operations, and MCP server configuration.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
Complete bundle: all Microsoft Skills for Fabric for developers and consumers.
Gelistet auf Cursor: cursor/plugins (5)
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Ask Databricks Genie questions about your workspace's data in plain language.
Gelistet auf Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
Sequential Thinking (Reference)
Dynamic and reflective problem-solving through thought sequences.
Gelistet auf Official MCP Registry (5)
-
Credit Optimizer v5 for Manus AI
Optimizes Manus AI credit usage by 30-75% via intelligent model routing and smart testing.
-
Execute cost-optimal-model-selector-mcp
Premium agentic endpoint for cost-optimal-model-selector-mcp.
-
Find the cheapest AI model that passes your tests: audit repo models, build evals, routing, sizing
-
Local-first LLM cost analysis and model-switch savings estimates for AI agents.
-
Intelligent LLM routing proxy — 60-90% cost savings by auto-selecting the cheapest model
Gelistet auf npm registry (MCP servers) (5)
-
mistral-mcp io.github.Swih/mistral-mcp
Mistral MCP server: extract invoices and documents from text, Markdown or OCR into typed JSON.
-
Run Claude Code subagents on cheaper opencode models (DeepSeek, opencode Go) with native parity.
-
One workspace for every AI coding assistant. Shared tasks, memory, and governance.
-
rubber-duck io.github.nesquikm/rubber-duck
Bridge to multiple LLMs and CLI agents: councils, debates, voting, and more
-
Shared project memory for Claude Code, Codex and Cursor: decisions and corrections through MCP.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Möchten Sie dieses Zeichen für Ihr Plugin in unserem Katalog?
Belegen Sie mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag, dass Sie es pflegen, und Sie können dieses Zeichen auf der Karte zeigen, dazu Live-Banner für Ihre Website und Ihr README. So funktioniert die Verifizierung
Außerdem erhalten Sie Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Community GitHub marketplaces. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.