agent-instructions

description	Architect a repository's AI-agent instruction files so one canonical source drives every tool without drift — AGENTS.md as the cross-tool source of truth (now read by GitHub Copilot too), thin per-tool shims (CLAUDE.md, GEMINI.md) that include it, and optional path-scoped .github/instructions/ rules. Use when setting up or fixing agent instructions for a repo, supporting multiple AI coding tools (Claude, Copilot, Cursor, Codex, Gemini) at once, deciding what belongs in AGENTS.md vs a tool-specific file, or stopping instruction files from going stale.
license	Apache-2.0
metadata	{"github-path":"agent-instructions","github-ref":"refs/tags/v1.5.0","github-repo":"https://github.com/devantler-tech/agent-skills","github-tree-sha":"ede64b81b2c321ce9680f852ed5f743ac28a04da"}
name	agent-instructions

Agent Instructions

Most AI coding tools read project guidance from a file in the repo — historically each looked in a different place (AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, …). Copy the same guidance into each one and the copies drift: a command changes in one file and the others keep telling agents the old way. The fix is one canonical source plus thin tool-specific shims (which include the canonical file). Keep all durable guidance in the canonical file; keep only genuine tool-specific quirks in a tool's own file.

The good news: AGENTS.md is now read by nearly every major tool — including GitHub Copilot — so the "one canonical file" ideal is finally achievable without a per-tool copy.