Why Subagent Reviews Stop Work
A postmortem of an AI coding research task where subagent reviews ran for 6 hours 36 minutes while the main experiment stayed at zero. Covers causes, prevention, detection, recovery, and reusable delegation rules.
Posts
AI coding, static sites, and product building
Field notes on AI coding tools, static-site operations, technical SEO, and small product decisions. Browse practical comparisons, troubleshooting guides, and operating retrospectives.
Are AI Coding Frameworks Better Than Vanilla? A Codex Experiment and Claude Code Research
A repeated Codex experiment comparing vanilla use, concise instructions, and AI coding frameworks, plus Claude Code research on success, runtime, tokens, and human intervention.
AI Coding Agent Permissions: What Is Safe to Auto-Approve?
A practical permission policy for Claude Code and Codex, covering file edits, tests, package installs, network access, Git, secrets, and deployment.
Does AGENTS.md Help Coding Agents? Why Studies Disagree on Success and Token Cost
A comparison of studies on AGENTS.md efficiency, repository-context success rates, and configuration bloat, with rules for what belongs in AGENTS.md and CLAUDE.md.
GitHub Pages Custom Domain with Cloudflare: DNS Records, Proxy, and Common Errors
A practical setup guide for connecting a GitHub Pages site to a Cloudflare-managed custom domain, including A records, CNAME, proxy status, HTTPS, and common Search Console errors.
Vercel vs Cloudflare Pages vs GitHub Pages: Which Free Static Hosting Is Actually Free?
A practical free static hosting comparison of Vercel, Cloudflare Pages, and GitHub Pages across pricing, limits, features, scalability, and migration timing.
No posts match this tag.