17 posts tagged with "tools"

Exit code 2 blocks an agent and feeds it a correction. Building a real TeammateIdle gate exposed three loop-safety rules the docs do not carry.

A second AI model that doesn't share Claude's blind spots catches more bugs than Claude reviewing itself. Here's how model stacking works.

Your CLAUDE.md goes stale fast. A stop hook can spawn a headless Claude session to review changes and propose rule updates after each turn.

Free Claude Code routes the Claude Code API to NIM, OpenRouter, DeepSeek, or local models. Setup walkthrough plus the harness for cheap models.

Claude Code vs Cursor compared for 2026. Agent teams, 1M context, fast mode, pricing tiers, and real workflow differences for developers.

Claude Code hooks for Windows, Linux, and macOS. One Node.js file, zero platform wrappers. Cross-platform patterns and working examples.

OpenClaw is a viral AI life assistant. Claude Code is a purpose-built coding agent. A developer's breakdown of when to use each tool.

Configure custom keyboard shortcuts in Claude Code. Reference for all 17 contexts, keystroke syntax, and keybindings.json examples.

Build Claude Code agents that validate their own output using PostToolUse hooks, Stop hooks, and read-only validator agents.

Set up a custom Claude Code status line showing model name, git branch, cost, and context usage. Includes ready-to-copy scripts.

Setup hooks combine deterministic scripts with agentic oversight. Automate installation, maintenance, and CI/CD with Claude Code.

Proactively backup your Claude Code session before compaction hits. StatusLine monitoring and threshold triggers keep your work safe.