AI / Agents / LLM (Frontier)

Cursor (.cursor/rules/)

Read the canonical `.github/instructions/ai.instructions.md` through `pwsh -NoProfile -File .frontier/runtime/frontier.ps1 cursor read <canonical-path>`.

by AgentHub Crawler·October 25, 2026·0 views·0 installs·Source ↗

Install

npx agentspec-cli install e1678769-a4ff-44b7-a3c1-e411334cbdec --file-type cursor-rules

→ .cursor/rules/

Rule Content

Cursor (.cursor/rules/)

---
description: AI / agent / LLM workflow standards (Frontier)
globs: **/*agent*,**/*llm*,**/*model*,**/*workflow*,**/agents/**,**/*ai*
alwaysApply: false
---

# AI / Agents / LLM (Frontier)

Read the canonical `.github/instructions/ai.instructions.md` through
`pwsh -NoProfile -File .frontier/runtime/frontier.ps1 cursor read <canonical-path>`.

- Pin model versions; define evaluation strategy and guardrails up front.
- Treat prompts as versioned artifacts; add tracing/observability hooks.
- Validate and sanitize model inputs/outputs; guard against prompt injection.

Similar Items

Rule

Project Name — Agent Instructions

This file is the entry point for any AI agent working on this repo.

by AgentHub Crawler

Rule

🚨 CRITICAL SYSTEM INSTRUCTION 🚨

Before answering ANY prompt or executing ANY code in this repository, you **MUST** first read and strictly adhere to ALL the rules defined in the following directory:

by AgentHub Crawler

Rule

Agents.md – Guidance for OpenAI Codex

This `Agents.md` file provides detailed instructions for OpenAI Codex and other AI agents collaborating on this repository. It includes project structure, conventions, testing, and update policies.

by AgentHub Crawler

Rule

Comments

Be the first to comment.