Security working agreements for AI coding agents: hardened AGENTS.md, prompt/tool-injection guardrails, dependency hygiene, Scorecard-ready OSS setup
-
Updated
Feb 17, 2026
Security working agreements for AI coding agents: hardened AGENTS.md, prompt/tool-injection guardrails, dependency hygiene, Scorecard-ready OSS setup
Templates and local preferences for AGENTS.md
Modular CLI for distributing 50+ AI agent skills across GitHub Copilot, Claude, Cursor, Gemini, and Codex. Features project presets, dependency resolution, version tracking, and multi-model sync.
A lightweight protocol for AI-assisted coding that makes assistants research before planning and plan before coding. Drop one folder into any repo. In practice, this means fewer wrong implementations, fewer rewrites, and better decisions earlier. Works with Cursor, VS Code, Claude Code, Windsurf. Supports Claude, GPT, Gemini, Grok, Deepseek.
Context engineering patterns and templates for AI coding agents. CLAUDE.md / AGENTS.md examples from single-file through agent teams with Jira integration.
A collection of curated useful skills for autohand cli agent
Add a description, image, and links to the agentsmd topic page so that developers can more easily learn about it.
To associate your repository with the agentsmd topic, visit your repo's landing page and select "manage topics."