$ cat /var/log/thoughts

Claude Code + Developer Tools

Posts matching all selected tags.

30 tips and tricks with Claude Code CLI on WSL

Claude Code on WSL returns fewer search matches than exist when a repo sits on /mnt/c. A 2,000-file benchmark, plus 30 fixes for the WSL boundary.

GuidesClaude CodeWindowsLinuxPerformanceDeveloper ToolsCLI1 min read · Jul 28, 2026

Claude Code vs Codex Limits, Measured in the Same Unit

Claude Code vs Codex limits, measured across 28 days and 56.8 billion tokens. Why token counts cannot predict quota burn, and what to read on each side instead.

Meta AnalysisAI CodingClaude CodeDeveloper ToolsComparisonMonitoringPerformance1 min read · Jul 28, 2026

Why expensive models make terrible execution subagents

Subagent model selection has one costly default. Reasoning models obey their own traces 15.6% of the time, so here is where to pin model and effort.

OpinionAI CodingClaude CodeDeveloper ToolsArchitecturePerformance1 min read · Jul 28, 2026

Token-Compression Skills Do Not Survive Measurement

Token compression skills report savings the invoice never shows. Cache reads carry 87 percent of an agent bill, and cutting tokens can push the cost up.

Meta AnalysisAI CodingClaude CodePerformanceDeveloper ToolsCaching1 min read · Jul 28, 2026

How claude skills were meant to be made (by hand)

Hand-written claude code skills outperform generated ones because they carry only the delta the model needs. Drop the bloat and survive every model upgrade.

OpinionClaude CodeAI CodingDeveloper ToolsProductivity1 min read · Jul 26, 2026

Every Model Release Ages Your Skills

Claude Code ignoring CLAUDE.md is often an aged file, not a model bug. See which instructions a release expires, and which lines to delete on day one.

Meta AnalysisClaude CodeAI CodingDeveloper ToolsProductivityAutomation1 min read · Jul 25, 2026

What Opus 5's Novel-Level Reasoning Benchmark Actually Means

Opus 5 novel reasoning rests on one number, 30.2% on ARC-AGI-3, and it scores action efficiency, not problems solved. Here are the four config lines to change.

Meta AnalysisAI CodingClaude CodeMLComparisonDeveloper Tools1 min read · Jul 25, 2026

6 Critics Grade My Post, Then Fix the Skill That Wrote It

Six critics grade the draft, then patch the SKILL.md that wrote it. The merge code, verdict ladder, and guardrails behind a self-improving Claude Code skill.

Meta AnalysisClaude CodeAI CodingDeveloper ToolsAutomationArchitecture1 min read · Jul 23, 2026

How to Write Claude Code Skills That Actually Trigger

Write Claude Code skills that actually trigger: fix the description-as-router, structure for progressive disclosure, and test in fresh sessions.

GuidesClaude CodeAI CodingDeveloper ToolsMCPProductivity1 min read · Jul 19, 2026