stetkeep
stetkeep stops Claude from refactoring code that's intentionally the way it is. Two pillars: 1) XML-structured behavior protocols (BRAIN/CRAFT/PERF, ~1.8K tokens each) encode…
Plugin-Paket · von chanjoongx
Überblick
stetkeep ist ein Plugin-Paket für KI-Coding-Tools von chanjoongx. 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.
stetkeep stops Claude from refactoring code that's intentionally the way it is. Two pillars: 1) XML-structured behavior protocols (BRAIN/CRAFT/PERF, ~1.8K tokens each) encode routing, refactor discipline, and measurement-first performance rules using the XML tagging pattern Anthropic's prompting guide recommends for reliable parsing. 2) A 16-entry false-positive catalog of patterns Claude commonly mis-flags as anti-patterns: 1000-line constants files (not God Files, just data tables), V8-optimized .map.map.map chains, below-fold <img> tags, useMemo that fixes reference-equality bugs. No other plugin in the directory ships this. Enforcement is mechanical, not prompted: permission deny-lists, PreToolUse hooks (safety-net.sh / .ps1), tool-scoped subagents that cannot Write new files, and path-scoped rules that auto-load CRAFT/PERF on src/** access. Honest 5-layer breakdown in ARCHITECTURE.md §1. Supply chain hardened: zero runtime dependencies, OIDC Trusted Publisher (no long-lived npm token), Sigstore SLSA v1 p
Was es abfragt
- Wird als Plugin-Paket installiert
- Deklarierte Hooks: 1
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 stetkeep@claude-communityWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Quelle auf GitHub öffnen) | Gelistet | 0.4.6 | Forks (GitHub): 0 Sterne (GitHub): 0 |
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.
Befehle: 3
brain-scancraft-auditperf-audit
Agenten: 3
brain-routercraft-specialistperf-specialist
Hooks: 1
PreToolUse
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.
-
A native Claude Code extension that prevents AI from over-refactoring your intentional code. Combines XML-structured protocols (BRAIN/CRAFT/PERF) with a 16-entry false-positive…
-
Blocks Claude Code from writing or committing leaked secrets.
-
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 that simplifies and refines code for clarity, consistency, and maintainability while preserving functionality. Focuses on recently modified code.
-
Session-local metacognition harness for long-running Claude Code work. When suggestions get reverted 3+ times within 10 tool calls, reflect invokes Opus 4.7 to reason about why…
-
Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context.
-
Enforces clean code principles across your project and fixes the code for you - not just flags what's wrong. Ships with 14 plain-language rules (formal textbook names in…
-
7 hooks for Claude Code covering safety, context injection, auto-formatting, model routing, and session lifecycle -- built from 6 months of daily use.
-
Six developer workflow commands for Claude Code: code review, security audit, test generation, test fixing, bug prediction, and documentation generation.
-
claude-meta-skills is a technical-preview reliability hook suite for Claude Code. It adds five local hook checks that help Claude catch common agent failure modes while working in…
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)
-
A native Claude Code extension that prevents AI from over-refactoring your intentional code. Combines XML-structured protocols (BRAIN/CRAFT/PERF) with a 16-entry false-positive…
-
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…
-
Session-local metacognition harness for long-running Claude Code work. When suggestions get reverted 3+ times within 10 tool calls, reflect invokes Opus 4.7 to reason about why…
-
Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context.
-
Enforces clean code principles across your project and fixes the code for you - not just flags what's wrong. Ships with 14 plain-language rules (formal textbook names in…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Agent that simplifies and refines code for clarity, consistency, and maintainability while preserving functionality. Focuses on recently modified code.
-
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.
-
Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
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.
-
Keep your coding agent up to date with the latest web best practices
-
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…
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
AI-powered code review in Codex, powered by CodeRabbit.
-
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.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
Gelistet auf Community GitHub marketplaces (5)
-
Blocks Claude Code from writing or committing leaked secrets.
-
Say it once. jevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, brings the relevant ones back next session, and checks…
-
Every Claude Code edit becomes a Causari event with its prompt, model and diff; ask `why` for any line. Needs the `re` binary from causari.dev.
-
Host adapters for CodeRifts: Claude Code PreToolUse asks before Write/Edit of OpenAPI, AsyncAPI, GraphQL, protobuf, or MCP manifest files. Not the GitHub Action…
-
archsteer io.github.einvoice-dev1/archsteer
Architecture governance for AI agents: query the live model, get target patterns, check files.
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Tools and techniques for maximizing GitHub Copilot effectiveness through better context management. Includes guidelines for structuring code, an agent for planning multi-file…
-
Preserves or recovers the reasoning behind a codebase — architectural decisions, rejected alternatives, workarounds, incident learnings, operational constraints, and historical…
-
Visualize and guide the GitHub Copilot Modernize CLI Assess, Plan, and Execute workflow for .NET, Java, and C++ application repositories.
-
Keep your coding agent up to date with the latest web best practices
-
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…
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.
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
Gelistet auf Cursor: cursor/plugins (5)
-
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.
-
Internal team workflows for CI, code review, shipping, local automation, and verification.
-
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.
-
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…
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.
-
MCP server for terminal commands, file operations, and process management
-
Tools and resources for writing Effect code in Typescript.
-
Educational Python refactoring assistant that provides guided suggestions for AI assistants.
-
MCP server for using Semgrep to scan code for security vulnerabilities.
Gelistet auf Official MCP Registry (5)
-
archsteer io.github.einvoice-dev1/archsteer
Architecture governance for AI agents: query the live model, get target patterns, check files.
-
Read-only context and complete checks against patterns learned from git history. Local; no LLM.
-
Automated codebase refactoring and type safety validator.
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
-
Production-safety audits for AI-generated code, with a fix for every finding.
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.