Developer Tools Codex plugins

Publisher keywords · listing

app builder ai app builder ai app builder no code mobile app builder web app builder iphone app builder android app builder no code app builder build an app with ai build a saas mvp builder mvp protot… …i アプリ制作 language learning app generador de apps build a prototype flashcard app workout tracker app running app vytvořit aplikaci diet app calorie tracker app water tracker app sleep tracker app ki app erstellen mood tracker app 怎么做app mobile app kaise banaye baby tracker app app prototype maker med…

Publisher full description

macOS development workflows for discovering local projects, building and running desktop apps, implementing native SwiftUI scenes, bridging into AppKit when necessary, adding lightweight Logger telemetry, triaging test failures, inspecting signing and entitlements, and debugging desktop-s…

Publisher full description

Design, implement, inspect and test MCP servers and interactive MCP Apps using focused skills for tool contracts, host-aware interfaces, secure integration, debugging, visual quality and release preparation. Start with an idea, API specification or repository; work th… …al workflow. Supports a useful tool-only fallback for clients without MCP Apps UI. Generated files, running tests, repository access and deployment depend on available host capabilities and user authorization; the plugin itself does not operate a hosted code-execution service.

Publisher description

…tings, backups, firewall rules, and DNS records • Start, stop, and restart services, and track long-running operations Access is restricted to services in your authenticated BoxToPlay account and the permissions granted to the app.

Publisher description

Control Plane skills, operating rules, and MCP server for building, deploying, and running containerized apps across AWS, GCP, Azure, Oracle Cloud, and your own hardware.

Publisher full description

Connect ChatGPT to a Mac you own or are explicitly authorized to manage. The Drive Commander Mac app requires macOS 14+ and must be installed, running, and paired with your account. Within the permissions you approve, Drive Commander can inspect and edit files in selected folders, run terminal and SSH commands, manage processes, use a browse…

Package name

app-6ab2816373dc81918d34014dccc50701

Package name

app-6a6f945292888191a7d77db4893f8520

Package name

app-69932d93c9088191a25748428bf3a1e4

Package name

app-6a6a699e6f3481918d5e6034432894f2

Package name

app-6a057d268ebc81919918d37eec718425

Publisher full description

Ansight gives your coding agent runtime evidence from real mobile apps, so it can debug and verify what actually happened instead of guessing from source code. Install the Ansight SDK into an iOS, Android, .NET MAUI, React Native, Flutter, or Capacitor app, and ever… …e window and correlate logs, failed requests, screenshots, and UI trees around an error • Operate a running app: boot a simulator or emulator, launch the app, tap and type through the semantic UI, and capture before-and-after evidence • Call remote tools the app exposes for authoritative in-process…

Publisher full description

Bilt lets you build mobile apps by chatting with an AI agent. From ChatGPT you can list and create Bilt projects, send instructions to the Bilt agent that writes and edits your app's code, answer the agent's clarifying questions, check whether a build is queued, running or paused, cancel a running build, and read a project's conversation history. Each response links to the project in Bilt, where you can preview the app, add secrets or connect Supabase. You ne…

Publisher description

Replit turns your ideas into real, running web apps and websites, with no coding or setup required. Describe what you want in plain language and Replit's AI Agent builds a working app for you (frontend, backend, database, and auth as needed), then…

Publisher full description

Edit existing web apps from ChatGPT. Connect a GitHub repository and ronda starts an isolated copy of the app with a running dev server and a live preview link. ChatGPT reads the code, makes small changes, checks the build output and shows you the result in the preview. Changes ChatGPT makes stay in the sandbox unti…

Publisher full description

…. Reading and writing are separate tools: queries run in a read-only transaction, and changes only happen through the write tool, which is marked as destructive so ChatGPT asks before running it. You can revoke access at any time in your SuperDB account.

Publisher full description

…nd use a PostgreSQL database that belongs to your account. - Publish static websites and expose web apps on public links when you choose to share them. - Schedule recurring jobs and one-off runs, and check their history later. Who it is for: developers, analysts, students, and creators who want thei… …never enter the conversation. Actions that change or delete data are marked so ChatGPT asks before running them. Limitations: an ATL Sandbox account is required. Accounts have usage limits on concurrent sandboxes, run time, storage, GPUs, and schedules, and running compute stops when an account rea…

Publisher full description

…subscription, person, or agent through a conversational no-write preview and a separate exact save approval. Then bring AtReady a goal, rough plan, or written plan before implementation to match saved tools, services, subscriptions, people, and agents to planner-provided work, expose material constraints and gaps, and explain its advice without contacting or running routed project resources. Codex owns the project plan. This local-first release requires a separately installed compatible project-atready runtime and local file access.

Publisher capabilities · listing

Write Modal Apps and Functions Run code on serverless GPUs Scale batch and parallel jobs Run untrusted code in Modal Sandboxes

Publisher full description

…platform from ChatGPT and Codex. Skills cover workspaces, jobs, compute environments, datasets, NetApp volumes, projects, apps, model endpoints and monitoring, MLflow experiment tracking, GenAI tracing, Flows, Spark/Ray/Dask, AI Gateway, governance, tags and properties, and the Domino Python and da… …ino deployment. The skills provide guidance and code; they don't connect to Domino on their own, so running jobs or calling APIs still requires your own Domino credentials.

Publisher description

Guides you through running a quantized language model on your own Apple Silicon Mac with mlx-optiq.

Publisher full description

…with a two-sample z-test. Starting or stopping an experiment and turning a feature flag on or off happen only on the ABMeter website, where you are signed in. Once an experiment runs, each user stays in the group they were first assigned to: the assistant cannot change its allocation or audiences,… …of your configuration from the conversation, including the hypothesis, description and metrics of a running experiment, parameter defaults and variants that no running experiment uses, and the audience or variant of a flag that is already on. A new account is empty. Ask the assistant to load the sam…

Publisher full description

…lic URL. It fetches the page, robots.txt, sitemap, and llms.txt the way an AI crawler does, without running JavaScript, and returns an A-F grade with a 0-100 score across nine categories: crawlability, understanding, answer readiness, citability, trust, content depth, freshness, AI-native signals, a… …ue by impact, and gives a plain-language fix for each one, with a copy-paste code snippet where one applies. The grade is weighted for the kind of page it is, so a homepage is not marked down for lacking an article's FAQ or publish date. AgentGrade reads public pages only and never changes anything.…

Publisher full description

CodeAgent Mobile lets you start, monitor, redirect and review long-running AI coding agents without leaving the conversation. Connect your CodeAgent account and ask for your sessions, send a task or a new instruction to an agent, answer the questions it asks, stop it… …est. Hand a session to your phone when you step away and keep supervising from the CodeAgent Mobile app. Works with the coding agents you already link in your CodeAgent account. Switching a session to another agent always asks for your confirmation first. Requires a CodeAgent Mobile account with at…

Publisher full description

…queues and monitor Redis health directly from your conversation. Built for developers and operators running background jobs, Durabull helps you diagnose backlogs, investigate failures, and recover work. Find jobs across queues, inspect redacted payloads, results, logs and stack traces, and review th… …equest a change, retry failed jobs, promote delayed jobs, or pause and resume queues. Supported MCP Apps hosts provide interactive queue, job, schedule, alert and health views. Connect Durabull Cloud or your self-hosted installation with scoped OAuth access. You need a Durabull account and permissio…

Publisher full description

…PowerShell, and show you the real output; - create and edit files in that folder; - check a service running on your computer, such as a local web app's health page. You stay in control. You choose which folders Local Commander can use, and writing files or running commands needs the permissions you set on your computer. Changes go through separ…

Publisher description

Keep a simulator beside the chat while building, running, or debugging iOS and Android apps. Stream devices, read native and Metro logs, analyze CPU and React profiles with TraceSift, render interactive CPU, memory, and FPS recordings, and control apps with Mobile Dev tools.

Publisher full description

Promptfoo skills for configuring providers and targets, writing eval suites, and setting up or running red team workflows against LLM apps.

Publisher description

Comprehensive skill for the entire Temporal lifecycle — developing applications, using the Temporal CLI, running and managing Temporal Server, and working with Temporal Cloud.

Publisher full description

…nd servers you control. Choose a saved project, inspect files, edit bounded text files, run locally approved commands, and review command activity and source changes. Active commands return progress and completion through server tools without requiring the workspace card or chat page to remain open. Your computer and companion must remain running; local approvals and host usage limits still apply. The plugin cannot restart a Chat turn that the host has ended or cancelled. Dedicated filesystem tools stay within approved roots; approved…

Publisher full description

…and files, create or edit text files, run development commands, read process output, interact with running processes, and revoke device access. Commands run with the local user's permissions and can modify files or contact external services. Device selection is required when multiple computers are online; an invalid explicit device identifier is rejected. Pairing uses a short-lived agent-bound approval code, and the long-lived device credential is delivered only to the local agent, never through MCP output. Tool calls may update usage counters, and the local runtime may retain arguments and…

Publisher full description

…ds, see which certificates or domains expire soon, and review CPU, memory and disk usage on servers running the Watchman Tower agent. If you allow it on the consent screen, the assistant can also add new monitors, pause and resume monitors, and delete monitors. Deletion is never immediate: a deleted… …when you connect; write access is opt-in. You can disconnect at any time from API Keys → Connected apps. Requires a Watchman Tower account on a plan with API access (Team or Stack).