jev
Cheap, fast, typed AI judgments inside Claude Code via the jevctl CLI: verify claims against evidence, screen fetched text for prompt injection, rank candidates by meaning, and…
Plugin-Paket · von Nasr Shaer
Überblick
jev ist ein Plugin-Paket für KI-Coding-Tools von Nasr Shaer. Marktplätze, die wir lesen und die es listen: 1 (Community GitHub marketplaces). Wir haben es erstmals am 2026-10-29 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-29.
Cheap, fast, typed AI judgments inside Claude Code via the jevctl CLI: verify claims against evidence, screen fetched text for prompt injection, rank candidates by meaning, and ask yes/no, multiple-choice, or rating questions.
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
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 Community GitHub marketplaces.
/plugin marketplace add nasrallah-al/jev-cli
/plugin install jev@jev-cliWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Community-Marktplatz nasrallah-al/jev-cli (Quelle auf GitHub öffnen) | Gelistet | 0.2.0 | Keine Zahl veröffentlicht | 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.
In einem Community-Marktplatz gelistet
| Marktplatz | Repository | Sterne (GitHub) |
|---|---|---|
| jev-cli | nasrallah-al/jev-cli | 22 |
Was das Paket enthält
So veröffentlicht auf Community GitHub marketplaces.
Skills: 1
jev
Befehle: 8
askclassifycompactextractfindroutescreenverify
Was sich geändert hat
- Wird seitdem als Produkt geführt
- 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.
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
epistemic-fault-line-audit-adrian-lerer
Audits legal AI outputs, prompts, skills, workflows and MCP/tool instructions for fluent but unsupported reasoning, missing evidence, overconfidence, hidden assumptions, weak…
-
Consult Jev for bounded typed second opinions during agent work: compare plans, check claims against supplied evidence, prioritize investigations, and challenge conclusions. Uses…
-
Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Score two AI outputs, get exact failure reasons, and issue a $0.01 USDC receipt via x402.
-
Decide, design, gate, judge, and defend evaluations for LLM, agent, and retrieval systems. Not ordinary unit tests.
-
LLM evaluation methodology and eval-suite design, based on Anthropic's evaluation guidance. /evals:methodology answers questions on success criteria, eval design, and grading…
-
Rosey – Quality verification for human and AI content
Fact-checks generated content against your sources of truth showing what to trust, change, & verify.
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)
-
Context engineering plugin for Claude Code — real-time prompt scoring, RLM adaptive weights, and token optimization. Scores every tool use across 5 dimensions (token utilization…
-
Claude Perfectionist audits your Claude Code instruction harness — CLAUDE.md, rules, hooks, settings, MCP config — and finds contradictions, missing verification, stale commands…
-
LGBTQIA+ safety tools for LLM engineers — audit prompts, review code, and catch harms before you ship
-
Break through difficult problems by gathering diverse AI perspectives in parallel. Consensus queries multiple AI providers concurrently — GPT-5.2, Gemini 3.1 Pro, and DeepSeek…
-
AI agent evaluation sandbox for Claude Code. Holdout scenario testing with Doer/Judge/Adversary/Observer roles, probabilistic satisfaction scoring, and append-only JSONL audit…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Output.ai workflow development toolkit for Claude Code. Adds 5 specialist agents (planner, builder, debugger, prompt writer, quality reviewer), 40+ slash-command skills covering…
-
Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects…
-
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
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Gelistet auf Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search…
-
Atlan data catalog plugin for Claude Code. Search, explore, govern, and manage your data assets through natural language. Powered by the Atlan MCP server with semantic search…
-
Speed up contract review, NDA triage, and compliance workflows for in-house legal teams. Draft legal briefs, organize precedent research, and manage institutional knowledge.
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
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.
-
Answer product and business questions with data
-
AI-powered code review in Codex, powered by CodeRabbit.
-
PostHog gives your AI agent direct access to your product analytics, feature flags, experiments, error tracking, surveys, logs, and LLM analytics. Ask questions about your data…
Gelistet auf Community GitHub marketplaces (5)
-
epistemic-fault-line-audit-adrian-lerer
Audits legal AI outputs, prompts, skills, workflows and MCP/tool instructions for fluent but unsupported reasoning, missing evidence, overconfidence, hidden assumptions, weak…
-
Consult Jev for bounded typed second opinions during agent work: compare plans, check claims against supplied evidence, prioritize investigations, and challenge conclusions. Uses…
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Decide, design, gate, judge, and defend evaluations for LLM, agent, and retrieval systems. Not ordinary unit tests.
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
Multi-model council for Copilot CLI: three subagents on different model families (Anthropic, OpenAI, Google) answer independently, then build on each other or attack the leading…
-
A runtime-portable 5-agent quality gate that adjudicates text artifacts before they ship. Five role-conditioned LLM deliberators run a 2-round async protocol with cross-read…
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
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…
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
Advanced Security plugin for GitHub Copilot.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
Gelistet auf Cursor: cursor/plugins (5)
-
Search company knowledge and draft verified answers.
-
Track AI visibility, sentiment, and citations.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
Enrich people and companies, run AI research agents.
Gelistet auf Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Production-ready RAG service to search and retrieve data from your documents.
-
Real-time web search, reasoning, and research through Perplexity's API
-
Analyze documents, images, videos, and audio.
-
Sequential Thinking (Reference)
Dynamic and reflective problem-solving through thought sequences.
Gelistet auf Official MCP Registry (5)
-
Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
-
Score two AI outputs, get exact failure reasons, and issue a $0.01 USDC receipt via x402.
-
Rosey – Quality verification for human and AI content
Fact-checks generated content against your sources of truth showing what to trust, change, & verify.
-
Local-first MCP server for LLM output verification — risk signals, injection and PII checks.
-
Scores whether AI assistants can read, understand and quote a public website. No account.
Gelistet auf PyPI (MCP servers) (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
air-blackbox-mcp io.github.airblackbox/air-blackbox-mcp
EU AI Act compliance scanner for Python AI agents. 14 tools across 6 articles.
-
Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.
-
Read, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline.
-
Connect AI assistants to Outline for document search, reading, and management
Gelistet auf npm registry (MCP servers) (5)
-
Build AI-powered forms, scored assessments and professional reports on FormLM, by natural language.
-
Typed AI judgments for agents: choice, score, and yes/no probabilities instead of prose.
-
jev_classify, jev_check, jev_score, jev_rank, jev_ask over MCP, plus the /jev skill.
-
dossier ai.imboard/dossier
MCP server for dossier automation standard - enables LLMs to discover, verify, and execute dossiers
-
AI visibility and SEO data for AI agents: citations, keywords, trends, and scheduled trackers.
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 Community GitHub marketplaces. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.