AGENTS.md patterns for context engineering in coding agents: safer command output, token efficiency, validation, and prompt-injection resistance.
-
Updated
May 8, 2026
AGENTS.md patterns for context engineering in coding agents: safer command output, token efficiency, validation, and prompt-injection resistance.
The tiny prompt that cuts your agent's yap by ~80% — Too Long Didn't Read.
THE META PROMPT 是一个专业化的提示词仓库,提供经过实战验证的结构化元提示词模板,旨在将通用大语言模型转化为具有增强可靠性和精确度的领域专用推理智能体。与传统提示词库不同,本项目专注于元级别的指令框架,支持系统化任务分解、基于角色的推理以及自我改进的智能体架构。
Sharable distillations of working-effectively-with-Claude-Code doctrines + tools (saga-21 corpus)
Agent brief writer for AI coding workflows: turns fuzzy requests into precise briefs with acceptance criteria, constraints, and verification steps.
Color-coded Codex prompt templates and Agent Skills for plugin-orchestrated AI coding workflows, MCP safety, repo intelligence, and automation.
An interactive parser for mapping folder architectures. Build, edit, and visualize directory structures using Pythonic indentation
Custom extensions for pi, the AI coding agent — multi-agent pipelines, UI middleware, GitHub workflows, and more.
Add a description, image, and links to the agent-prompts topic page so that developers can more easily learn about it.
To associate your repository with the agent-prompts topic, visit your repo's landing page and select "manage topics."