Agents-Md

8 practitioners working with Agents-Md:

AGENTS.md is for your repo. self.md is for YOU. your repo gets an instruction file. why don't you? the case for a personal identity protocol in the age of AI agents.

AGENTS.md vs CLAUDE.md vs INSTRUCTIONS.md every AI coding tool has its own config file. here's what they're called, how they differ, and what actually matters.

andrej-karpathy-skills a single CLAUDE.md file derived from andrej karpathy's observations on LLM coding pitfalls. the first claude skills repo built around one specific thinker's body of work.

context engineering eats prompt engineering in 48 hours, four tools shipped that turn your context file into linted, testable, version-controlled infrastructure. prompt engineering quietly stopped being the interesting layer.

context engineering eats prompt engineering, and somebody finally measured the regression four tools shipped in 48h to lint your AGENTS.md. one user proved Claude got 67% dumber. skills got auto-recorded from your screen. the day prompt engineering quietly stopped being interesting.

failure-derived: AGENTS.md science, invisible configs, and who owns your model's behavior the first study of whether AGENTS.md files actually work, a silent A/B test reshaping Claude Code users' outcomes, a Pi Zero AI agent, and the sovereignty question hiding inside heretic's 891-star week

MCP Security: Why Nobody Audits AI Agent Permissions AI agents get filesystem and database access without code review. Here's what developers are doing about the trust vs control problem.

ok-skills curated AI coding agent skills and AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SKILL.md-compatible tools.