This repository is a curated collection of system prompts, tool definitions, and behavioral configurations extracted from dozens of commercial and open-source AI coding assistants and products. It contains over 100 text files organized by vendor (Anthropic, Cursor, VSCode Agent, Manus, Devin, Replit, etc.), each representing a snapshot of how these AI agents are instructed to behave, what tools they can use, and what safety rules they follow. The collection is not an application or a data pipeline; it is a reference archive for researchers, prompt engineers, and developers studying AI agent design patterns, prompt injection risks, and competitive analysis. The repository includes both full system prompts (e.g., Claude Code 2.0, Cursor Agent, Manus) and structured tool JSON schemas that define function-calling APIs. While the content is valuable for understanding AI agent architecture, the repository itself has no executable code, no versioning of individual prompts, and no automated validation, making it a static snapshot rather than a living project.
This Python application automates the registration of new Cursor IDE accounts, including browser-based sign-up, email verification code retrieval (via tempmail.plus or IMAP/POP3), and updates of Cursor's local authentication tokens and machine identifiers. It serves as a workaround for Cursor's trial limitations by continuously generating fresh accounts. The architecture is a monolithic script with modular components: a browser manager (DrissionPage), email handler, configuration loader, authentication database updater, and machine ID resetter. The entry point is `cursor_pro_keep_alive.py`, which offers two modes: reset machine code only or full registration flow. The code is functional but not highly polished; it relies on third-party email services and browser automation that may break with Cursor or service changes. The project is explicitly deprecated by the author, who recommends alternative tools like Claude Code.
cursor-vip is a client-side Go/TUI application that lets users share Cursor IDE Pro accounts. At runtime it presents a terminal wizard: it fingerprints the machine (MAC-based device ID + machine-id), contacts a private licensing backend (hardcoded hosts: cursor.jeter.eu.org), prints the user's promotion stats, expiry, and payment links, then starts one of several "modes" that make the locally installed Cursor app authenticate as a shared Pro user. Mode 1 is the minimalist mode; modes 2-4 run a local MITM proxy (go-mitmproxy fork) that requires the user to install a trusted root certificate and intercepts Cursor's API traffic, with mode 3 doing free-trial account rotation and mode 4 providing a dedicated "exclusive" account. The core Cursor-manipulation code lives in an `auth/` package absent from this snapshot - go.mod shows it vendors local forks of `machineid` and `go-mitmproxy` - so the visible code is only the client shell, payment flow, and OS plumbing. Architecturally it is a monolith split into packages: `tui` (terminal UI with embedded i18n locale files for 7 languages), `tui/client` (HTTP client using beego v1's httplib against the private API), `tui/shortcut` (a global keyboard hook recognizing typed 3-letter codes like `sm1`/`u3d`/`buy` to switch modes, refresh accounts, or buy access), and `tui/tool` (OS utilities: locale detection, system-proxy configuration for Windows/macOS/Linux, flock-based single-instance enforcement, and MAC fingerprinting). The build script targets 3 OSes x 3 architectures and obfuscates most binaries with `garble`, consistent with a grey-market licensing tool that expects to be reverse-engineered. The project is actively maintained (last commit March 2026) and clearly works for its user base, but the code is average quality: global mutable state in a `params` package, string-concatenated endpoint paths, no tests or CI, an unconditional `mode = 3` override bug in `GetConfig`, and deprecated dependencies (beego v1, dgrijalva/jwt-go v3.x). It also has a questionable security posture - it instructs Mac users to disable SIP, asks for a trusted root CA for the MITM proxy, and requires Windows admin privileges. Engineers should not reuse this codebase as-is for legitimate licensing work; the genuinely extractable parts are the cross-platform OS utilities (locale detection, proxy toggling, single-instance lock, device fingerprinting).
This repository is a curated 'awesome list' of links to external Agent Skills repositories. It contains no application code, data pipelines, or executable software. Its sole function is to serve as a community-maintained index and directory. The README is meticulously organized by vendor and category, with contribution guidelines, quality standards, and a security notice. While it has no software components to extract, it is a highly effective and well-maintained directory for its domain. It is not a software application and has zero reusability as a codebase.