Developer Tools Codex plugins

Package name

chronos

Publisher full description

…ntion is justified. Optional silent hooks accelerate lifecycle hints without creating model turns. Chronos also diagnoses Windows degradation, quota and context pressure, approval and review loops, permission-rule problems, rollout duplication, and SQLite churn. No publisher telemetry.

Package name

pathrule

Publisher keywords · listing

pathrule context memory rules skills mcp

Package name

thrixel

Publisher keywords · listing

3d game assets glb threejs browser game thrixel

Publisher

Thrixel Inc.

Publisher description

…ames 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.

Publisher full description

…3D game you can play in the browser. It settles what you are making, generates the 3D models with Thrixel (game-ready .glb files you own), writes the three.js game around them (scene, controls, UI and touch input), and publishes it to a public thrixel.world link you can share. Everything runs on Th…

Publisher keywords · listing

chrome web store firefox add-ons browser extensions store rankings chrome web store ranking chrome extension analytics browser extension analytics extension analytics chrome web store seo keyword rank…

Publisher description

Keyword rank tracking, extension analytics, and competitor analysis for Chrome Web Store extensions and Firefox add-ons. Review user growth, ratings, and ranking history, and manage tracked keywords and competitors.

Publisher full description

Keyword rank tracking and competitor analysis for Chrome Web Store extensions and Firefox add-ons. Bring extension analytics into ChatGPT to review user growth, ratings, and search visibility over time. Research the market: search the public catalog,…

Publisher description

…e board and task list for AI coding agents that cannot talk to each other directly. Agents post to threads, join with role badges, pass the baton to whoever acts next, and keep a Task List, all inside the signed-in user's private workspace.

Publisher full description

…r AI coding agents that cannot talk to each other directly. An agent in one tool posts to a shared thread; another agent, in a different tool or on another machine, reads it and replies. The thread lives on the hub rather than in a terminal, so it is still there after a session ends. With Giljo Agen…

Publisher full description

Use callable API-first tools injected into external Chrome, build missing reusable tools, and send privacy-safe feedback.

Publisher description

Build a deliberately throwaway prototype whose purpose is to answer a design, state, logic, or UI question before committing to the real implementation.

Publisher description

Investigate files, URLs, domains and IP addresses with VirusTotal threat intelligence. Read existing reports and interpret detections together with analysis dates and coverage. A missing report is an unknown result, not a safety verdict. Analyze an explicitly authori…

Publisher full description

…es the proposed local action with accepted evidence, reuses matching results, permits changed work through typed invalidation, and shows what may be skipped versus what still must run. Do not use rate-limit percentage as stop authority; it gates only the duplicate action and never stops the task, pu…

Publisher full description

…d cycle-time stages, the AI-vs-no-AI comparison with its classification coverage, velocity and the throughput forecast, daily activity and rate-limit pressure, adoption and skill reuse, model usage and reliability, capture coverage, and (admins only) spend versus the prior period, ROI, cost per merg…

Publisher full description

…s • Ask why a run failed and get the errors, stack traces, screenshots and traces behind it • Step through a run's Playwright trace, action by action, to see what the page did • Find the root cause and fix the test, flaky ones included • Compare a pull request's runs with main to see what the change…

Publisher full description

…ser confirmation in Geodd DeployPad; full key secrets remain in the console and are never returned through chat. Billing changes, payments, and direct GPU provisioning are not supported.

Publisher full description

…prove the job is done. You approve the exact version. - You choose a fixed-length package and pay through a secure Stripe checkout page outside ChatGPT. The scope and end date are agreed up front, with no bidding. - You see three vetted engineers who differ in experience, stack, country and industr…

Publisher description

…ile a mission from an issue in your tracker, or from a title and a description. Follow the mission through its stages, and read its verdicts, cost and session logs. Send an instruction to the agent that runs next, or leave a note for it. Read the proof that a run produced, such as test traces and sc…

Publisher full description

…current-version test evidence into listing copy, capabilities, starter prompts, five positive and three negative review cases, and release notes. Missing or conflicting evidence remains explicit. The plugin does not judge product quality, operate the OpenAI portal, submit, publish, or guarantee app…

Publisher full description

…e, and your team reviews and approves the changes it finds. The SnapVisor plugin lets ChatGPT work through that review with you. What it can do: - Show who you are connected as and which accounts you can use. - List your projects, open one, and read account analytics. - List a project's builds, open…

Publisher full description

…eck hosted SOFA connection status, find and inspect agent knowledge, contribute reusable knowledge through guarded workflows, and record read-first votes or verification outcomes.

Publisher description

Connect ChatGPT to your TurboStack hosting: hosts, Health, Threat Center, monitoring and deploys.

Publisher full description

…ts in your own TurboStack account, so you can ask about them in plain language instead of clicking through the interface. What you can do: - List your hosts and read their TurboStack configuration - Review Health issues and incident and analysis reports, and get advice on what to fix first - Check T…

Publisher full description

…declarations, upload and job-flow guidance, offline mock examples and partner access requirements through MCP. This connection provides documentation. Live try-on requires separately approved Partner API access and backend credentials. This documentation connection does not generate images, access…

Publisher full description

…sualization to choose, design, implement, test, and export browser charts, dashboards, maps, WebGL/Three.js scenes, Canvas/D3 visuals, Gantt charts, UML/software diagrams, scrollytelling, reports, PDFs, and slide decks. It emphasizes source-backed data, accessible responsive layouts, URL-shareable a…

Publisher description

Search and read Alicia's published Three.js, Houdini and real-time 3D garden notes with canonical source citations.

Publisher full description

…nd read Alicia's published technical notes from digitalgarden.si, an interactive 3D garden. Covers Three.js, WebGPU and WebGL plant rendering, Houdini, glTF and USD, Gaussian splats, and coding-agent experiments. Results include original text, canonical URLs, authorship, publication dates and availa…

Publisher description

Create narrated video code reviews and visual walkthroughs of pull requests, repositories, and algorithms.

Publisher full description

…Give it code, a diff, or context from your repository, and Video Code Reviewer turns it into a walkthrough in your language — with voiceover, highlighted code, before-and-after comparisons, diagrams and animations. See what changed, understand why it matters, and share the explanation with your team…

Publisher full description

…ded. Requires a local coding assistant, Node.js 22+, installed package dependencies and Playwright Chromium.

Publisher full description

…er production or real accounts. Requires a local coding assistant, Node.js 22+, npm and Playwright Chromium on macOS or Linux. The test engine itself needs no paid model API calls.