perf
Structured performance investigation with baselines, profiling, and evidence-backed decisions — run by AI agents inside your editor. `/perf` enforces a rigorous 10-phase…
Plugin-Paket · von agent-sh
Überblick
perf ist ein Plugin-Paket für KI-Coding-Tools von agent-sh. Marktplätze, die wir lesen und die es listen: 1 (Claude Code: claude-plugins-community). Wir haben es erstmals am 2026-10-11 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-12.
Structured performance investigation with baselines, profiling, and evidence-backed decisions — run by AI agents inside your editor. `/perf` enforces a rigorous 10-phase methodology derived from recorded real investigation sessions: establish a baseline, identify the breaking point, generate hypotheses, profile, run controlled experiments, measure, document. No random micro-optimizations; every change is baselined, isolated, measured, and either kept or reverted with evidence. Designed to keep the agent honest in a domain where intuition is usually wrong.
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
Keine Daten für einen automatischen Befehl: Die Angaben der Marktplätze sagen nicht eindeutig, wie man es verbindet.
Wo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Quelle auf GitHub öffnen) | Gelistet | 5.1.0 | Forks (GitHub): 0 Sterne (GitHub): 3 |
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.
Was das Paket enthält
So veröffentlicht auf Claude Code: claude-plugins-community.
Skills: 8
perf-analyzerperf-baseline-managerperf-benchmarkerperf-code-pathsperf-investigation-loggerperf-profilerperf-theory-gathererperf-theory-tester
Befehle: 1
perf
Agenten: 6
perf-analyzerperf-code-pathsperf-investigation-loggerperf-orchestratorperf-theory-gathererperf-theory-tester
Was sich geändert hat
Bei diesem Plugin hat sich nichts bewegt, seit wir es beobachten.
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.
-
CodSpeed is the all-in-one performance testing toolkit. Dive into benchmarking results, flamegraphs, and performance comparisons — give Claude granular profiling context to…
-
Run Codeflash as a background agent in Claude Code to automatically optimize Python, Java, JavaScript, and TypeScript code for performance. Codeflash analyzes your code…
-
Full-stack engineering ops for Claude Code. One command (/prodmasterai) covers your entire dev lifecycle: orchestrate features into parallel tasks, run 11-phase QA with health…
-
AI code review that catches production-breaking bugs, business logic issues, and security vulnerabilities — directly in Claude Code.
-
A Claude Code skill that reviews codebases top-down: WHY (goal) → WHAT (architecture) → HOW (implementation) → improvements ranked by leverage. The antidote to surface-level LLM…
-
Line-level Python profiler skill for Claude Code. Profile any package or script to find exactly which lines are slow, then optimize iteratively.
-
perfloop ai.perfloop/perfloop
Always-on performance engineering for your own code: proven pull requests, the merge stays yours.
-
Plugin description Code quality review plugin based on Frontend Fundamentals 4 principles (readability, predictability, cohesion, coupling). Supports React and Angular with…
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
A Claude Code plugin that provides CodeScene Code Health analysis tools and skills for reviewing, refactoring, and safeguarding code quality.
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)
-
CodSpeed is the all-in-one performance testing toolkit. Dive into benchmarking results, flamegraphs, and performance comparisons — give Claude granular profiling context to…
-
Run Codeflash as a background agent in Claude Code to automatically optimize Python, Java, JavaScript, and TypeScript code for performance. Codeflash analyzes your code…
-
Full-stack engineering ops for Claude Code. One command (/prodmasterai) covers your entire dev lifecycle: orchestrate features into parallel tasks, run 11-phase QA with health…
-
AI code review that catches production-breaking bugs, business logic issues, and security vulnerabilities — directly in Claude Code.
-
A Claude Code skill that reviews codebases top-down: WHY (goal) → WHAT (architecture) → HOW (implementation) → improvements ranked by leverage. The antidote to surface-level LLM…
Gelistet auf Claude Code: claude-plugins-official (5)
-
CodSpeed is the all-in-one performance testing toolkit. Dive into benchmarking results, flamegraphs, and performance comparisons — give Claude granular profiling context to…
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
-
New Relic observability intelligence for Claude Code. Investigate APM performance, analyze cloud costs, debug Kubernetes, write NRQL queries, and respond to alerts — all from your…
-
Detect AI agents in your codebase and instrument them with Pendo Agent Analytics via the best-fit path: Python SDK, TypeScript SDK, client-side trackAgent, or the Conversations…
Gelistet auf Claude: knowledge-work-plugins (5)
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Keep your coding agent up to date with the latest web best practices
-
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…
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
Streamline engineering workflows — standups, code review, architecture decisions, incident response, and technical documentation. Works with your existing tools or standalone.
Gelistet auf 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.
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
Inspect recent issues and events in Sentry from Codex.
-
Qodo setup, code intelligence, and review workflows.
Gelistet auf Community GitHub marketplaces (5)
-
CodSpeed is the all-in-one performance testing toolkit. Dive into benchmarking results, flamegraphs, and performance comparisons — give Claude granular profiling context to…
-
Sourcery security findings for AI coding agents: triage and minimal-change remediation via the public Sourcery API (12 MCP tools + skills).
-
Dash0 Observability
OpenTelemetry observability for OpenAI Codex sessions. Captures prompts, tool calls, MCP calls, sub-agent activity, and token usage as OTel traces.
-
Aikido Security scanning for Claude Code — SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.
-
Dynatrace observability skills: DQL query patterns, application and infrastructure monitoring, log analysis, problem investigation, and incident response workflows, with the…
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Helps GitHub Copilot investigate mobile app telemetry, diagnose crashes, manage [bitdrift](bitdrift.ai) workflows and dashboards, integrate the Capture SDK into iOS, Android, and…
-
Visualize and guide the GitHub Copilot Modernize CLI Assess, Plan, and Execute workflow for .NET, Java, and C++ application repositories.
-
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…
-
Model, visualize, and deploy applications with Radius from the GitHub Copilot app and CLI.
-
Inspect a repository, improve Tiny Tool Town readiness, submit its listing issue, and launch remediation work.
Gelistet auf 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.
-
Analyze MSVC build performance using vcperf.exe and ETL traces.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
Gelistet auf Cursor: cursor/plugins (5)
-
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…
-
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.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Internal team workflows for CI, code review, shipping, local automation, and verification.
Gelistet auf Docker MCP Catalog (5)
-
Educational Python refactoring assistant that provides guided suggestions for AI assistants.
-
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
-
next-devtools-mcp is a Model Context Protocol (MCP) server that provides Next.js development tools and utilities for AI coding assistants.
-
Tools and resources for writing Effect code in Typescript.
-
MCP server for terminal commands, file operations, and process management
Gelistet auf Official MCP Registry (5)
-
perfloop ai.perfloop/perfloop
Always-on performance engineering for your own code: proven pull requests, the merge stays yours.
-
Gemini-powered MCP server for code review analysis.
-
Java profiling with AI agent integration. Profile CPU, memory, JDBC, HTTP and more.
-
Security + bug + perf + refactor audit for Python. Returns 0-10 score + MD report.
-
Community of Consciousness MCP Server — upload and explore collective wisdom via GitHub.
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.
Ist das Ihr Plugin?
Fügen Sie es Ihren Projekten hinzu und belegen Sie, dass Sie es pflegen: mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag. Sie erhalten 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 Claude Code: claude-plugins-community. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.