Developer Tools Codex plugins

Publisher subtitle

Extract any website's design

Publisher capabilities · listing

OCR extraction, PDF-to-Markdown/JSON conversion, table and layout extraction, conversion validation

Publisher description

Extract API contract details, check whether documentation covers the stated API contract, and compare API contract versions. Results are structured, evidence-based, and limited to explicitly provided…

Publisher description

Extract explicit API changes, classify breaking changes, and map evidence-based impacts across consumers, tests, and documentation. Uses only the facts supplied by the user and does not access externa…

Publisher description

…int that fits. Covers file conversion (Word, PDF, Excel, images), document generation, OCR and text extraction, data validation (email, phone, VAT, IBAN, tax IDs), enrichment, geolocation and IP data, currency and unit conversion, QR and barcode generation, archive handling, and AI utilities. Search…

Publisher description

…int that fits. Covers file conversion (Word, PDF, Excel, images), document generation, OCR and text extraction, data validation (email, phone, VAT, IBAN, tax IDs), enrichment, geolocation and IP data, currency and unit conversion, QR and barcode generation, archive handling, and AI utilities. Search…

Publisher description

…nd generating design systems, loading UI/UX and React Native guidance, reviewing interface quality, extracting existing CSS tokens, and installing icon components. Tools are served from a public HTTPS endpoint and authenticated with OAuth for hosted ChatGPT and Codex use.

Publisher full description

…fely, and return clean web data for reasoning. Use BrowserAct when an agent needs to browse, click, extract, fill forms, upload files, work inside logged-in sites, or run repeatable browser workflows. Requires the Browser Act CLI.

Publisher full description

…ves and backups, or restore previous versions when needed. - Analyze assets with AI — detect faces, extract text, get color palettes, and accessibility scores. - Monitor usage — track storage, bandwidth, and transformation credits in real time. - Visual search — find visually similar images by uploa…

Publisher description

…data inside ChatGPT. Search for current information, read a known page as Markdown, crawl websites, extract schema-shaped JSON, parse documents, retrieve company and brand intelligence, inspect visual design systems, run asynchronous scraping batches across thousands of URLs, and monitor websites fo…

Publisher description

…nts. In ChatGPT, users can search the web, scrape one or many public pages, map and crawl websites, extract structured facts, and query DataBlue's catalog of structured data APIs.

Publisher description

Parse, extract, classify, and split documents from chat: pull fields, tables, and line items out of PDFs, images, Office files, and spreadsheets, identify document types, break bundles into separate document…

Publisher description

…web, at a lower token cost per answer. Search finds current pages with ranked results and snippets. Extract returns clean, structured content from any URL, including pages needing JavaScript or interaction. Extraction Templates give consistently shaped records from known sites. Web Search Agents han…

Publisher description

Parallel Search provides drop-in web search and content extraction capabilities. The tools invoke the Search API and Extract API endpoints and ensure effective use by agents. Find content on the web without wasting tokens.

Publisher full description

…ration, speech transcription, cloud notifications, arbitrary OS audio automation, screenshot action extraction, or silent installation and hook-trust bypass.

Publisher full description

Use Webcmd's bundled webcmd-browser skill from Codex to drive a real browser: inspect, click, type, extract, and capture network calls in authenticated sessions. Webcmd keeps sitemap memory locally so later runs need less exploration. Requires the @agentrhq/webcmd npm CLI.