Developer Tools Codex plugins

Publisher subtitle

Run 180+ AI models as tools

Publisher subtitle

AI models + app hosting

Publisher capabilities · listing

…and evaluation boundaries Build or improve RAG pipelines when coding tools and project access are available Diagnose ingestion, chunking, indexing, retrieval, reranking, and context failures Evaluate ranking, grounded answers, citations, abstention, and regressions by slice Review data isolation, pr… …ntainment, safe rollback, and incident recovery Compare vector search, hybrid retrieval, rerankers, models, and trade-offs Add tracing for answer evidence, latency, cost, failures, and index freshness Coordinate real specialist agents where supported; otherwise work sequentially Prepare regression c…

Publisher capabilities · listing

Understand repository architecture and existing code contracts Debug failures from error messages, logs, tests, and trace evidence Implement focused changes with regression tests and minimal diffs Review code for correctness, security, concurrency, and compatibility Ref… …and data pipeline code Harden LLM client, tool, and structured-output integrations Productionize ML models and exploratory notebooks Triage incidents and prepare evidence-backed release handoffs Coordinate supported specialist agents for complex changes

Publisher full description

…ality check, and troubleshoot common problems such as running out of memory. It states the limits plainly: KV-cache quantization saves memory but can slow decoding, long contexts need memory, and quantized models should be checked on your own tasks instead of trusting speed numbers. This plugin contains instructions only; everything runs on your own machine.

Publisher full description

Use OpenAI Developers to build AI applications and agents. Optimize your existing API integration with our latest models and best practices, and build multimodal experiences with voice and image models. Build agents with the Agents API and OpenAI-hosted sandboxes, and create voice agents with the new GPT Live bid…

Publisher capabilities · listing

Recent changes to Claude Code, Codex and Pi, with official sources New coding-relevant models from tracked labs, with open-weights status Attributed takes from trusted AI-coding practitioners A weekly briefing formatted for sharing with a team

Publisher capabilities · listing

Create persistent hosted AI agents Configure agent instructions, models and supported tools Run agents and continue their conversations Read agent replies, run status and tool activity Schedule one-time or recurring agent tasks Answer pending agent questions, appro…

Publisher capabilities · listing

Generate speech from text (TTS) Transcribe audio with timing (STT) Meeting AI: upload recordings, get transcripts and notes Upload audio files from ChatGPT or by link Remove background noise (voice isolation) Chat completions with Aisha LLM List voices and models

Publisher description

CrowdStrike Charlotte AI AgentWorks skills for creating, managing, and invoking AI agents via external Falcon API Gateway endpoints. Includes agent lifecycle management, invocation, knowledge base operations, and discovery of models/tools/templates.

Publisher capabilities · listing

View connected account profile View available AI models Create API keys through secure browser confirmation Review masked API key access Review inference usage and rate limits Monitor request volume, success rates, errors, and average/peak RPM Check…

Publisher capabilities · listing

…ct metrics, funnels and experiments Recommend fit-for-purpose application architectures Define data models, API contracts and integration boundaries Plan bounded, testable AI-powered features when justified Review security, reliability, privacy, accessibility and cost needs Compare build-versus-buy options and technology tradeoffs Create phased engineering plans and han…

Publisher capabilities · listing

Turn an idea into a dApp spec Recommend AI models for a build Explain TokenOS build and deploy capabilities

Publisher full description

Connect AtlasBurn to see where your AI spend is going across models, providers, workflows, and agents. Ask ChatGPT to break down usage and costs, identify expensive requests or unusual spending patterns, investigate retries and costly agent behavior, and review…

Publisher full description

…eir Codiedev reporting, right in the conversation. Ask how engineering is doing this month, whether AI-assisted pull requests actually merge faster, which repositories drive AI spend, how adoption is going on a team, or which models people use and how reliable they are. Who it's for: company admins, CTOs and team managers whose company uses Codiedev to capture AI coding sessions and pull requests. Admins see the whole comp…

Publisher full description

…ld on the DataRobot platform from your development environment. Use these skills to prepare data, train and explain models, deploy and monitor models, make predictions, automate DataRobot application delivery, operate workloads, and add observability to existing applications. The skills guide DataRobot Python SDK a…

Publisher full description

Design circuit boards with AI, from your first idea to the files your manufacturer needs. Describe what you want to build in everyday language, or start with the pin assignments in your firmware. Choose from over one million el… …connectors, and microcontrollers. Build with real catalog parts, their footprints, and available 3D models—from a simple LED circuit to a custom electronics project. Create and edit schematics, generate PCB layouts with automatic component placement and routing, and refine your design through conver…

Publisher full description

Connect to the Hugging Face Hub to explore Models and Datasets, access SDK Documentation and more. Manage Machine Learning Jobs and connect to thousands of AI applications via Spaces.

Publisher description

Manage LaunchDarkly feature flags, AgentControl Configs (AI agent prompts/models), experiments, guarded and automated rollouts, segments, metrics, dashboards, alerts, and observability data (logs, traces, errors, sessions) directly from chat. Create and target flags, run an…

Publisher full description

Ultralytics YOLO skills help Codex build computer-vision models end to end, in Ultralytics Platform or local code. Choose the right YOLO model, upload and annotate datasets, train on cloud or local GPUs, improve accuracy, and run inference, tracking, and Solutions such as object counting, then export to ONNX, TensorRT, CoreML, Core AI, OpenVINO, or NPU formats or deploy a d…

Publisher full description

Inspect model usage and request logs in your connected ZRouter account. List available models, manage virtual model routers, and set account budgets and rate limits. This plugin cannot create API keys, access credit balances or purchases, or send model requests. Some account features de…

Publisher capabilities · listing

Plan from a local model and agent registry Choose the lowest-cost eligible route Explain rejected options Require independent high-risk review Never call a provider

Publisher full description

…ams and developers write, debug, review, adapt and tune SQL. Its focused workflows examine output grain, joins, duplicates, NULL and time semantics, SQL dialects, incremental/CDC logic, schema migrations, BI models and safe data changes. Performance advice is grounded in query-plan evidence where available. It works from the context and tools explicitly provided in the host; this skills-only plugin does n…

Publisher name · package

ArcanEdge AI

Publisher full description

KnowzCode is a structured AI coding framework for ChatGPT and Codex — not a notes app, not “the Knowz codebase.” The knowledge stays. The model doesn’t. The model is interchangeable. Your context is not. Your data. Your models. Your terms. Use KnowzCode when you want durable coding context: analyze → spec → build with TDD → audit → ship, with quality gates between phases. Micro fixes stay light; full features get the…

Publisher full description

Build voice ai and multimodal agents with Pipecat, from an idea to a local app and Pipecat Cloud deployment. Explore speech-to-text (STT), language models (LLMs), text-to-speech (TTS), real-time speech-to-speech and other supported multimodal patterns using Pipecat documentation, API definitions and example code. Explore the documentation and exa…

Publisher full description

…s you through adaptive-classifier, an open-source Python library for text classifiers built on pretrained language models that learn new examples and new classes without retraining from scratch. The workflow helps you decide whether the library fits your problem (small labeled sets, label sets that change, routing…

Publisher full description

Show a vehicle directly in your conversation or add it to a page, email or document. Find a make, model and year in the catalog, then render it on a transparent background in eight camera views and any paint color. Signed image URLs load without an API key in the browser. Decode VINs, fetch catalog make logos, or create textured 3D models in GLB, USDZ and FBX formats.

Publisher full description

Codex Advisor helps software developers review architecture, API interfaces, data models, and migration plans in Codex CLI and Codex desktop. Each consultation returns one recommendation with tradeoffs, risks, and acceptance checks. Advisor sends bounded technical context to OpenAI for inference through your authenticated account and allowance; Zero Delta runs no relay or telemetry backend and does not automatically receive consultation packets or responses. Redacted receipts…

Publisher full description

…thon 3.11+, Git and an installed, authenticated Codex CLI on your own account; no account access or models are provided. Use a standalone skill for local Codex CLI or IDE workflows. Plugin discovery depends on your host version and provider; executor plugin installation and IDE plugin discovery remain unverified. See the project's support matrix for recorded evidence. ChatGPT web is not a supported execution surface. Runs locally with your user privileges; slices use Git worktrees, which are no…

Publisher full description

Build facial verification into your app without hosting machine-learning models. This plugin helps your coding agent connect the deepface.dev API, compare two face photos, generate face embeddings and handle verification results in your existing stack. It guides account si… …s tool. A deepface.dev account is needed to call the hosted API. The account owner confirms their email and accepts the service terms. Facial similarity is not proof of identity or liveness.

Publisher full description

…y bugs. Powered by ethskills.com, an open-source knowledge pack that fixes the stale Ethereum facts AI models get wrong.

Publisher description

Access the authoritative EzzyBills developer specification, REST API contracts, authentication models, and integration guidance for building EzzyBills applications such as approval dashboards, email response workflows, and purchase order tools.

Publisher description

…o generation with the Runway API and official SDKs. Connect to your Runway Dev account to inspect available models and task errors, manage Model Routers and live avatars, and inspect recorded routing decisions.

Publisher full description

…r: developers building sports apps, betting tools, odds comparison sites, sports analytics, trading models or AI agents that need a sports odds API, a sportsbook odds feed or a sports data API. Limitations: the plugin covers API providers only. It has no live odds, no scores and no match data, and it gives no…

Publisher description

Build playable 3D browser games with AI-generated assets, right in ChatGPT. The build-world skill takes an idea to a finished three.js game: Thrixel generates, refines and textures the game-ready .glb models, and the game is published to a public thrixel.world link anyone can play.