context-tax: price what Claude Code sends before you type
At a glance
CLI reads Claude Code transcripts to show per-turn context cost—what ships before the first keystroke, unused payload, and skills that never reached the agent—so you can trim defaults instead of guessing. This workflow is listed under context-window, cost, claude-code, observability, coding-agents.
junegunn (fzf author) documents how shell CTRL-T bindings die once you live in an agent prompt—and how tmux PREFIX bindings restore fzf: tmux-fzf-complete (files/dirs/URLs/on-screen paths/sentences) and fzf-git.sh (commits, branches, PRs) inject selections as keystrokes into Claude Code or Codex. Requires tmux 3.7+ floating panes and agent settings that keep scrollback (/tui default for Claude Code; Codex alternate_screen=never). Pattern: make agent prompts as completable as the shell.
Agent Standup (OSS, local) turns Claude Code, Codex, Mistral Vibe, and Cowork sessions into a live stand-up: desks, screen-share of real commands/diffs, voices, replay + recap; `npx @double_geste/agent-standup --open`; VS Code/Cursor extension and Claude Code plugin. Free; optional Halloween character pack from €2.
Claude Code now gzip-compresses large request bodies to api.anthropic.com even when telemetry is off (opt out with CLAUDE_CODE_GZIP_REQUEST_BODIES=0). Anthropic’s ClaudeDevs also noted conversation gzip cut local first-token wait (p90, excluding model time) roughly 4.07s→1.33s and cloud 16.99s→6.00s—same harness, snappier agent loops without a new model.
Local-first npm app: isometric office UI where each Claude Code session gets a desk; red windows flag waits for you, with tmux integration—watch many agents without scrolling terminals.