supergraph
Supergraph là plugin cho Claude Code, kết hợp hai phương pháp: - **Superpowers** (obra): Bắt buộc AI tuân theo quy trình làm việc có kỷ luật — brainstorm, plan, TDD, review…
Plugin-Paket · von datit309
Überblick
supergraph ist ein Plugin-Paket für KI-Coding-Tools von datit309. Marktplätze, die wir lesen und die es listen: 1 (Claude Code: claude-plugins-community). Wir haben es erstmals am 2026-10-12 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-13.
Supergraph là plugin cho Claude Code, kết hợp hai phương pháp: - **Superpowers** (obra): Bắt buộc AI tuân theo quy trình làm việc có kỷ luật — brainstorm, plan, TDD, review. - **Code-review-graph** (tirth8205): Phân tích cấu trúc code bằng AST graph — blast radius, hub nodes, community detection, surprise scoring. ### Vấn đề supergraph giải quyết **Không có supergraph:** User: "Thêm authentication cho API" AI: *đọc toàn bộ 27,700 file* *viết code không có kế hoạch* *không viết test* *gửi PR* Tokens: ~443,200 Chất lượng: không đảm bảo **Có supergraph:** User: "Thêm authentication cho API" AI: 1. get_stats → "Repo: 27,700 file, 12 communities, 8 languages" 2. Brainstorm → "JWT hay session? Endpoint nào?" 3. blast_radius(["src/auth/"]) → "15 file bị ảnh hưởng, 2 hub nodes" 4. Plan → 6 task, mỗi task 2-5 phút, có bước verify 5. TDD → viết test trước, implement sau, refactor 6. Auto-fix → chạy test + lint + review, tự sửa nếu lỗi 7. Review → blast_radius xác nhận tất cả file đã xử lý Tokens: ~4,260 Chất lượng: pro
Was es abfragt
- Wird als Plugin-Paket installiert
- Deklarierte Hooks: 4
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 supergraph@claude-community
Wo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Quelle auf GitHub öffnen) | Gelistet | 1.0.0 | Forks (GitHub): 6 Sterne (GitHub): 22 |
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: 7
reviewsupergraph-contextsupergraph-executesupergraph-fixsupergraph-integrationsupergraph-plantdd
Agenten: 2
executorplanner
Hooks: 3
PostToolUsePreToolUseStop
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.
-
codegraphcontext-mcp com.clauxel.codegraphcontext/codegraphcontext-mcp
A paid remote MCP for code graph MCP for AI coding, built to return verdicts, receipts, usage logs,
-
seshat-mcp ai.papyruslabs/seshat-mcp
Structural code intelligence for AI agents: real call graphs, blast radius, and change history.
-
Dual-graph code context engine for Claude Code. Builds a structural call graph and dependency graph of your codebase, then delivers precise file and symbol recommendations before…
-
Query a precomputed code graph (nodes, edges, summaries) of TS/JS/React/Next.js/Node repos via MCP.
-
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
-
Senior craftsman methodology for Claude Code. 22 commands, 12 specialized agents, and automated hooks that enforce DDD, Clean Architecture, and TDD practices. Includes 3-level…
-
Cross-repository semantic code intelligence for AI coding agents, from a local code graph.
-
codemesh io.github.pyalwin/codemesh
Intelligent code knowledge graph for AI coding agents — 71% cheaper, 72% faster
-
Your AI's live map of your codebase — every call, dependency, and contract indexed across your repos, shared across every running agent via a local daemon. Gives Claude Code 52…
-
ai-architect-mcp-codebase io.github.cdeust/ai-architect-mcp-codebase
Codebase intelligence MCP — index any repo into a property graph; 26 tools for agents.
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)
-
Dual-graph code context engine for Claude Code. Builds a structural call graph and dependency graph of your codebase, then delivers precise file and symbol recommendations before…
-
Senior craftsman methodology for Claude Code. 22 commands, 12 specialized agents, and automated hooks that enforce DDD, Clean Architecture, and TDD practices. Includes 3-level…
-
Your AI's live map of your codebase — every call, dependency, and contract indexed across your repos, shared across every running agent via a local daemon. Gives Claude Code 52…
-
Watch how your code flows instead of reading about it. Your AI agent emits an animated, drillable diagram you watch, pause, and drill into - no more 400-line bullet walls.
-
Comprendo gates AI implementation behind a visual developer approval step. When you type /comprendo <task>, Claude reads your codebase, builds a structured plan with before/after…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
-
Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
-
Apollo GraphQL agent skills for Claude Code — Apollo Client, Server, Federation, Connectors, Router, Rover CLI, iOS, Kotlin, and the Apollo MCP server. Covers schema design, query…
-
Teamwork Graph CLI is Atlassian's agent-first interface to your entire work context: Jira issues, Confluence pages, Bitbucket PRs, along with your connected third-party data…
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
Gelistet auf Claude: knowledge-work-plugins (5)
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Streamline engineering workflows — standups, code review, architecture decisions, incident response, and technical documentation. Works with your existing tools or standalone.
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
Keep your coding agent up to date with the latest web best practices
-
Build and deploy Base44 full-stack apps with CLI project management and JavaScript/TypeScript SDK development skills
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
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 web apps with frontend asset design, browser testing, UI components, payments, and database guidance.
Gelistet auf Community GitHub marketplaces (5)
-
Apollo GraphQL agent skills for Claude Code — Apollo Client, Server, Federation, Connectors, Router, Rover CLI, iOS, Kotlin, and the Apollo MCP server. Covers schema design, query…
-
Local graph memory that lets Codex recall project context across sessions.
-
Teamwork Graph CLI is Atlassian's agent-first interface to your entire work context: Jira issues, Confluence pages, Bitbucket PRs, along with your connected third-party data…
-
Endor Labs workflow agents and setup for Claude Code.
-
Comprehensive development workflow for building AI agents with the Atomic Agents framework. Includes specialized agents for schema design, architecture planning, code review, and…
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Model, visualize, and deploy applications with Radius from the GitHub Copilot app and CLI.
-
Teamwork Graph CLI is Atlassian's agent-first interface to your entire work context: Jira issues, Confluence pages, Bitbucket PRs, along with your connected third-party data…
-
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…
-
Generic cross-repo command center canvas for GitHub Copilot with onboarding, focus planning, repo health, work signals, and session cleanup.
-
Meta prompts that help you discover and generate curated GitHub Copilot agents, instructions, prompts, and skills.
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Advanced Security plugin for GitHub Copilot.
-
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.
-
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…
-
Render PR diffs as review canvases grouped by importance.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
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.
-
Manage repos, issues, pull requests, and Actions.
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.
-
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
-
Tools and resources for writing Effect code in Typescript.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Tools for interacting with Git repositories.
Gelistet auf Official MCP Registry (5)
-
codegraphcontext-mcp com.clauxel.codegraphcontext/codegraphcontext-mcp
A paid remote MCP for code graph MCP for AI coding, built to return verdicts, receipts, usage logs,
-
seshat-mcp ai.papyruslabs/seshat-mcp
Structural code intelligence for AI agents: real call graphs, blast radius, and change history.
-
Query a precomputed code graph (nodes, edges, summaries) of TS/JS/React/Next.js/Node repos via MCP.
-
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
-
Cross-repository semantic code intelligence for AI coding agents, from a local code graph.
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.