AddyOsmani.com - How to write a good spec for AI agents

kept by eddie jan 14

Writing effective AI agent specs requires a high-level vision, structured PRD-like format, modular task breakdowns, and built-in guardrails to keep agents focused and productive.

GitHub - tobilg/ai-observer: Unified local observability for AI coding assistants
AI Observer is a self-hosted, single-binary OpenTelemetry observability backend that tracks token usage, costs, latency, and errors across multiple AI coding assistants via a local dashboard.
also on Gemini CLI, GitHub Copilot, Claude Code, #ai-coding, #developer-tools
What Actually Is Claude Code’s Plan Mode?
Claude Code's plan mode is a thin prompt overlay and read-only guard, not a fundamentally different execution path.
also on #prompt-engineering, Claude Code, Anthropic, #ai-coding, #developer-tools
Changes in the system prompt between Claude Opus 4.6 and 4.7
Opus 4.7's system prompt adds child safety tags, a tool-search mechanism, anti-verbosity instructions, and drops the Trump presidency clarification from the 4.6 prompt.
also on #prompt-engineering, Claude Code, Anthropic, #developer-tools
Show HN: A plain-text cognitive architecture for Claude Code
Cog provides a structured plain-text memory system for AI coding agents, enabling shared context across tools like Claude Code and Cursor without a server or database.
also on Gemini CLI, Claude Code, #ai-agents, #ai-coding, #developer-tools
Skill engineering and the case against one-shot AI design
Paul Bakaus argues AI agents need “skill engineering” to give designers precise control, rejecting full automation in favor of human judgment steering the final 20% of creative work.
also on GitHub Copilot, Claude Code, Anthropic, #ai-agents, #ai-coding, #developer-tools