projectb-sdk

Build programmatic agent integrations using Codex or legacy Cursor SDKs.

Updated May 28, 2023
One-click install
npx skills add https://github.com/steveulrich/ProjectB --skill projectb-sdk-steveulrich
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: projectb-sdk
Source: https://github.com/steveulrich/ProjectB/tree/main/.agents/skills/projectb-sdk
Command: npx skills add https://github.com/steveulrich/ProjectB --skill projectb-sdk-steveulrich

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Choosing the wrong SDK packages, APIs, or runtime when building a programmatic agent integration leads to rewrites and broken deployments. This Skill identifies whether the target is a current OpenAI Codex runtime or a legacy Cursor-compatible host before any code is written, then guides the integration accordingly. ## Core Features & Use Cases - Runtime Detection: Distinguishes current Codex integrations from legacy Cursor-compatible hosts so the correct SDK packages, paths, and tool schemas are used. - Language Inference: Infers TypeScript versus Python from repository signals like package.json, pyproject.toml, or existing source files, stating a reversible default when signals are absent. - Legacy Reference Gating: Loads the legacy Cursor SDK reference (covering Agent.prompt, Agent.create, Agent.resume, local vs cloud runtimes, MCP servers, and disposal patterns) only after the host is explicitly verified as Cursor-compatible. - Use Case: A developer asks to automate code review agents in CI. The Skill checks the runtime, picks the correct SDK and language, and produces a working integration without mixing Codex and Cursor APIs. ## Quick Start Use the projectb-sdk skill to build a programmatic agent integration for this repository and tell me which runtime and SDK packages to use.

Frequently Asked Questions about projectb-sdk

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a programmatic agent integration with the Codex SDK?▼

First identify whether the host is a current Codex runtime or a legacy Cursor-compatible environment, then infer TypeScript or Python from repository files. Use the official Codex documentation for current integrations and the legacy reference only for verified Cursor hosts.

Should I use the TypeScript or Python agent SDK?▼

Choose based on explicit user naming first, then codebase signals: package.json or tsconfig.json indicates TypeScript, while pyproject.toml or requirements.txt indicates Python. When no signal exists, state a reversible default and proceed rather than blocking on the choice.

What is the difference between local and cloud agent runtimes?▼

Local agents run on the caller's machine against the current working directory and reuse local credentials. Cloud agents run on a hosted VM against a freshly cloned repository, suiting long jobs and automated pull request creation.

Why does my agent run locally when I wanted a cloud agent?▼

The SDK silently defaults to local when neither local nor cloud options are set, producing no error. Always pass the runtime configuration explicitly, such as cloud repository settings or a local working directory, to avoid this trap.

When should I not use the legacy Cursor SDK reference?▼

Do not load the legacy Cursor reference for current Codex tasks, since its package names like @cursor/sdk and cursor-sdk are not Codex defaults. Use it only after explicitly verifying the host is Cursor-compatible, including its packages, paths, and tool schema.