How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
u9401066AGENTS.mdu9401066/pubmed-search-mcp/AGENTS.md
Shared workspace guidance for agent clients that can read AGENTS.md. Use this file for cross-tool baseline rules. Keep agent-specific behavior in tool-native locations such as .github/copilot-instructions.md or .clinerules/ so the…
u9401066AGENTS.mdu9401066/nsforge-mcp/AGENTS.md
Workspace instructions for autonomous agents (Copilot, Cline, Codex, OpenHands, Hermes, …) working in the Neurosymbolic Forge (NSForge) repository. Help build and operate NSForge — an MCP server that turns concepts into verifiable, traceable entities (symbols → derivations → algorithms). The AI orchestrates; deterministic tools reify. See docs/reification-ladder-direction.md for the north star. Every symbol / equation / value / line of code in a final result must have a tool call as its "birth certificate" (provenance). The AI must not hand-derive…
u9401066AGENTS.mdu9401066/asset-aware-mcp/AGENTS.md
This guide covers the consolidated 1.4.1 operations. Discover the installed runtime contract and enabled flags before use; check GitHub Releases for publication status. Keep releases on 1.4.x and consolidate verified changes; do not bump the version for each feature. MCP provides necessary checks; the Agent performs complete semantic/visual review and corrections. These are workspace instructions for Codex when working with Asset-Aware MCP through the VS Code extension, local CLI, or MCP server. Help the user build and operate citation-ready document…
u9401066AGENTS.mdu9401066/medical-image-agent-harness/AGENTS.md
This repository contains a provider-neutral research harness for auditable medical image co-reading. It does not contain a viewer, screen capture, PACS writeback, commercial model integration, or autonomous diagnostic workflow. - Use uv for Python environments and run uv run pytest plus uv run python scripts/check_compatibility.py after meaningful changes. - Keep the canonical agent method in .agents/skills/medical-image-reading/; do not duplicate it under another skill discovery directory. - For medical-image reading or evaluation tasks, load the medical-image-reading skill and only the modality…
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.
