token-audit
Local audit of Claude Code token usage. Nine detectors (Opus-on-simple, context rot, CLAUDE.md bloat, hook bloat, skill-description overhead, Bash anti-patterns, tool-schema…
Paquete de plugins · de Bayram Annakov
Resumen
token-audit es un paquete de plugins para herramientas de programación con IA publicado por Bayram Annakov. Marketplaces que leemos y que lo publican: 1 (Community GitHub marketplaces). Lo vimos por primera vez el 2026-10-15 y desde entonces no hemos registrado cambios. Según nuestra pasada por los marketplaces del 2026-10-16.
Local audit of Claude Code token usage. Nine detectors (Opus-on-simple, context rot, CLAUDE.md bloat, hook bloat, skill-description overhead, Bash anti-patterns, tool-schema dumping, cache churn, redundant reads). Ranked by impact with fix actions. Cites Anthropic's Claude Code team.
Qué pide
- Se instala como paquete de plugins
Ninguno de los marketplaces que leemos publica sus herramientas ni los ajustes que pide.
Lo que declara, pide y ejecuta, completo
Instala solo plugins de desarrolladores en los que confíes. Mostramos lo que publican los marketplaces y no probamos plugins.
Funciona con
- Claude Code
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por ti ni probamos plugins.
Como plugin de Claude Code
Generado a partir de lo que declara Community GitHub marketplaces.
/plugin marketplace add bayramannakov/token-audit-skill
/plugin install token-audit@token-audit-skillDónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Marketplace de la comunidad bayramannakov/token-audit-skill (Abrir el código en GitHub) | Publicado | 0.1.0 | Sin cifra publicada | Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
Figura en un marketplace de la comunidad
| Marketplace | Repositorio | Estrellas (GitHub) |
|---|---|---|
| token-audit-skill | bayramannakov/token-audit-skill | 12 |
Qué contiene el paquete
Tal como se publica en Community GitHub marketplaces.
Skills: 1
token-audit
Qué cambió
- Pasó a ser un producto que seguimos
- Community GitHub marketplaces: apareció
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta lista.
-
Audit your Claude Code harness: research-backed enforcement mapping, bloat detection, completeness checks, and best-practices review.
-
Two 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…
-
Reports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
-
Pre-execution cost estimation for LLM agent workflows with calibration learning
-
Context hygiene for Claude Code: drift detection, re-read dedup, and token analytics.
-
Agent Smith adds two slash commands to Claude Code: /analyze-agent performs a full configuration audit across 7 evaluation pillars (Security, Instruction Clarity, Configuration…
-
Token-efficiency workflow for Claude Code — cuts discovery and follow-up context by 60-90% using QMD BM25 path helpers and RTK output compression.
-
Persistent worktree-local Codex CLI triage for Claude Code, with bounded reviews and exact-candidate required approval.
-
Token-budgeted codebase context for Claude Code. One call to auto_context gives Claude the optimal context for any task — automatically selecting, ranking, noise-filtering, and…
-
Automatic code review, adversarial review, and rescue via Codex through OpenRouter.
Plugins similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en Claude Code: claude-plugins-community (5)
-
Two 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…
-
Agent Smith adds two slash commands to Claude Code: /analyze-agent performs a full configuration audit across 7 evaluation pillars (Security, Instruction Clarity, Configuration…
-
Token-budgeted codebase context for Claude Code. One call to auto_context gives Claude the optimal context for any task — automatically selecting, ranking, noise-filtering, and…
-
AI code review that catches production-breaking bugs, business logic issues, and security vulnerabilities — directly in Claude Code.
-
A research-backed code review plugin for Claude Code that orchestrates parallel concern-specialized agents, cross-validates findings with deterministic verification, and produces…
Publicado en Claude Code: claude-plugins-official (5)
-
Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
-
Aikido Security scanning for Claude Code — SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.
-
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
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects…
Publicado en Claude: knowledge-work-plugins (5)
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
MCP server for terminal commands, file operations, and process management
Publicado en Codex: openai-curated (openai/plugins) (5)
-
AI-powered code review in Codex, powered by CodeRabbit.
-
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.
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
Qodo setup, code intelligence, and review workflows.
Publicado en Community GitHub marketplaces (5)
-
Audit your Claude Code harness: research-backed enforcement mapping, bloat detection, completeness checks, and best-practices review.
-
Reports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
-
Pre-execution cost estimation for LLM agent workflows with calibration learning
-
Context hygiene for Claude Code: drift detection, re-read dedup, and token analytics.
-
Agent Smith adds two slash commands to Claude Code: /analyze-agent performs a full configuration audit across 7 evaluation pillars (Security, Instruction Clarity, Configuration…
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Shows live prompt-cache reuse, expiry, token composition, and AI Credit cost for the current GitHub Copilot session without making model calls.
-
Analyze 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…
-
Meta prompts that help you discover and generate curated GitHub Copilot agents, instructions, prompts, and skills.
-
Inspect current and historical GitHub Copilot token and AI-credit usage with per-agent rollups and in-canvas session drill-down.
-
Build applications with the GitHub Copilot SDK across multiple programming languages. Includes comprehensive instructions for C#, Go, Node.js/TypeScript, and Python to help you…
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Advanced Security plugin for GitHub Copilot.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Navigate and interact with your C++ code using the Microsoft C++ Language Server.
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
Publicado en Cursor: cursor/plugins (5)
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Skills 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…
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
Publicado en Docker MCP Catalog (5)
-
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Educational Python refactoring assistant that provides guided suggestions for AI assistants.
-
MCP server for using Semgrep to scan code for security vulnerabilities.
-
MCP server for terminal commands, file operations, and process management
Publicado en Official MCP Registry (5)
-
Reports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
-
Pre-execution cost estimation for LLM agent workflows with calibration learning
-
Context hygiene for Claude Code: drift detection, re-read dedup, and token analytics.
-
Cut AI agent token costs 5-15x — routes only relevant code symbols instead of full files.
-
Release-truth gate for AI-generated code. Hosted MCP server is closed-source (Narapa LLC).
Encontrados por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Quieres esta marca para tu plugin en nuestro catálogo?
Demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS, y podrás mostrar esta marca en la ficha, con banners en vivo para tu web y tu README. Cómo funciona la verificación
Además recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Datos de Community GitHub marketplaces. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.