74 posts tagged with "guide"

Claude Code cross-session messaging lets your sessions message each other. How ListAgents and SendMessage work, inbound controls, and the limits.

Eighteen agent definitions went from 8,798 lines to 664 and got better. What died: persona theater, THINK HARD, emoji. What survived, and why.

Anthropic cut 80% of Claude Code's system prompt. We ran the same surgery on a production framework: 8,798 agent lines to 664. Here is the diff.

Claude got it wrong. Model problem or effort problem? The diagnostic that tells you which dial to turn, plus the effort field on every subagent.

An agent that finished and one silently blocked look identical. The two delivery models, why self-reports are not evidence, and what to check.

Every CLAUDE.md guide tells you what to add. After Claude 5, subtraction wins. The delete list, the one test per line, and what must never be cut.

Fable 5 rewards a briefed outcome and punishes step-by-step prompting. Six practices for Claude Code, plus where Opus 5 still wins.

When Claude Code multi-agent orchestration saves money and when it adds a 60% markup for nothing. The coordination cost math, measured.

A hidden Claude Code subagent watches another agent and reports drift. Observer agents: the enable flag, the digest, and the ObserverReport tool.

The Anthropic vs OpenAI race put frontier models in every ChatGPT and Claude tier. For moderate to heavy users, $100 on each lab beats $200 on one.

Claude Code runs four loop types: turn-based, goal-based, time-based, and proactive. What each means and how to set a real stop condition.

What Claude Code /compact keeps and loses, straight from Anthropic's docs. The full survival table plus how to make rules and skills persist.