claude-crap
Deterministic Quality Assurance plugin for Claude Code. CRAP stands for Change Risk Anti-Patterns — a metric originally developed by Alberto Savoia and Bob Evans at Google in 2007…
Plugin-Paket · von ahernandez-developer
Überblick
claude-crap ist ein Plugin-Paket für KI-Coding-Tools von ahernandez-developer. Marktplätze, die wir lesen und die es listen: 2 (Claude Code: claude-plugins-community, Community GitHub marketplaces). Wir haben es erstmals am 2026-10-11 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-15.
Deterministic Quality Assurance plugin for Claude Code. CRAP stands for Change Risk Anti-Patterns — a metric originally developed by Alberto Savoia and Bob Evans at Google in 2007 to identify code that is both complex and under-tested. Inspired by their work. Claude-crap wraps every Write, Edit, and Bash tool call with a PreToolUse gatekeeper, a PostToolUse verifier, and a Stop quality gate backed by the CRAP index, Technical Debt Ratio, tree-sitter AST metrics, and SARIF 2.1.0 reports. Auto-detects and runs ESLint, Semgrep, Bandit, and Stryker at boot so users get real A..E quality grades out of the box. Forbids the agent from writing functional code before a test safety net exists (the Golden Rule).
Was es abfragt
- Wird als Plugin-Paket installiert
- Einstellungen: 1
- Deklarierte Hooks: 5
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 Claude Code: claude-plugins-community.
/plugin marketplace add anthropics/claude-plugins-community
/plugin install claude-crap@claude-communityWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Quelle auf GitHub öffnen) | Gelistet | 0.4.8 | Forks (GitHub): 4 Sterne (GitHub): 9 |
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.
Auch in einem Community-Marktplatz gelistet
| Marktplatz | Repository | Sterne (GitHub) |
|---|---|---|
| herz | ahernandez-developer/claude-crap | 9 |
Was das Paket enthält
So veröffentlicht auf Claude Code: claude-plugins-community.
MCP-Server: 1
claude-crap
Skills: 4
adoptanalyzecheck-testscore
Hooks: 5
PostToolUsePreToolUseSessionStartStopSubagentStop
Was sich geändert hat
- Auf einem neuen Marktplatz erschienen: Community GitHub marketplaces
- 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.
-
Five intelligence systems for Claude Code. Analyze instruction quality, generate deeper tests, scan for security vulnerabilities, understand codebase architecture, and trace how…
-
Is your Claude Code setup actually good? This plugin tells you. It scans your CLAUDE.md, hooks, rules, and settings, gives you a score out of 100, and auto-fixes what's broken…
-
Agent Smith adds two slash commands to Claude Code: /analyze-agent performs a full configuration audit across 7 evaluation pillars (Security, Instruction Clarity, Configuration…
-
Runs Claude Opus bug hunters in parallel, locally on one issue or in Anthropic's cloud on a repository, and returns findings proven by failing tests and reproducers, with clean…
-
A full lifecycle software development partner for Claude Code - from concept to completion.
-
Multi-agent development harness for Claude Code. Your AI has speed; we give it direction — through living specs and focused specialist agents.
-
Config-driven guardrails for Claude Code
-
Six developer workflow commands for Claude Code: code review, security audit, test generation, test fixing, bug prediction, and documentation generation.
-
Evidence-first Claude Code plugin for repeatable, spec-driven development workflows.
-
Generic Claude Code development harness — TDD pipeline, subagents, quality gates, and deploy workflow.
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)
-
Five intelligence systems for Claude Code. Analyze instruction quality, generate deeper tests, scan for security vulnerabilities, understand codebase architecture, and trace how…
-
Is your Claude Code setup actually good? This plugin tells you. It scans your CLAUDE.md, hooks, rules, and settings, gives you a score out of 100, and auto-fixes what's broken…
-
Agent Smith adds two slash commands to Claude Code: /analyze-agent performs a full configuration audit across 7 evaluation pillars (Security, Instruction Clarity, Configuration…
-
A full lifecycle software development partner for Claude Code - from concept to completion.
-
Multi-agent development harness for Claude Code. Your AI has speed; we give it direction — through living specs and focused specialist agents.
Gelistet auf Claude Code: claude-plugins-official (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…
-
Aikido Security scanning for Claude Code — SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.
-
Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
-
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
-
Your code review partner. CodeRabbit provides external validation using a specialized AI architecture and 40+ integrated static analyzers—offering a different perspective that…
Gelistet auf 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…
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
The Vanta plugin connects Claude Code to Vanta's security and compliance platform through the Vanta MCP server. It combines Vanta's test-specific remediation intelligence with…
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
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.
-
Qodo setup, code intelligence, and review workflows.
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
Gelistet auf Community GitHub marketplaces (5)
-
Agent Smith adds two slash commands to Claude Code: /analyze-agent performs a full configuration audit across 7 evaluation pillars (Security, Instruction Clarity, Configuration…
-
Runs Claude Opus bug hunters in parallel, locally on one issue or in Anthropic's cloud on a repository, and returns findings proven by failing tests and reproducers, with clean…
-
A full lifecycle software development partner for Claude Code - from concept to completion.
-
Config-driven guardrails for Claude Code
-
Generic Claude Code development harness — TDD pipeline, subagents, quality gates, and deploy workflow.
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Visualize and guide the GitHub Copilot Modernize CLI Assess, Plan, and Execute workflow for .NET, Java, and C++ application repositories.
-
Automatically enforce SonarQube code quality and security in the agent coding loop — 7,000+ rules, secrets scanning, agentic analysis, and quality gates across 40+ languages…
-
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…
-
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.
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.
-
Navigate and interact with your C++ code using the Microsoft C++ Language Server.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
Gelistet auf Cursor: cursor/plugins (5)
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
Internal team workflows for CI, code review, shipping, local automation, and verification.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
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.
Gelistet auf 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.
-
Educational Python refactoring assistant that provides guided suggestions for AI assistants.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants.
-
MCP server for terminal commands, file operations, and process management
Gelistet auf Official MCP Registry (5)
-
Twelve tools to inspect CRAP scores, find work, and check edited functions against their ceiling.
-
Context hygiene for Claude Code: drift detection, re-read dedup, and token analytics.
-
Make a coding agent prove it: run the repo's real tests, typecheck and lint before it says done.
-
Production-safety audits for AI-generated code, with a fix for every finding.
-
agent-audit io.github.fullstackdegen/agent-audit
Turn Lighthouse audits into coding-agent fix packs for Claude Code, Cursor, and Copilot.
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 Claude Code: claude-plugins-community. 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.