RRulestackinrulestack.hashnode.dev·1d ago · 4 min readYour GitHub Actions cron fires less often than you declared: what we measured and how to design for itWe run an automated publishing pipeline entirely on GitHub Actions cron schedules — no server, no queue, just workflows that wake up, do one thing, and commit the result. It mostly works. But there is00
RRulestackinrulestack.hashnode.dev·2d ago · 5 min readA Claude Code subagent costs ~436k tokens before it reads a single file: measured, with the break-even mathEvery guide to Claude Code subagents tells you the same two things: they isolate context, and they parallelize work. Both true. What none of them told us was the number that actually decides whether a00
RRulestackinrulestack.hashnode.dev·3d ago · 6 min readWhen your MCP tool fails: errors, hangs, and empty results — what Claude Code actually does with eachYesterday I posted a one-liner on Bluesky: an MCP tool that errors teaches the model something, one that hangs teaches it nothing. A reply pointed out a third case that is worse than both — the tool t00
RRulestackinrulestack.hashnode.dev·5d ago · 7 min readWe cut our CLAUDE.md from 548KB to 34KB: what loads when, measured — and the commit gate that keeps it smallOur CLAUDE.md was 548KB. Every session — including every subagent — loaded all of it before doing any work. One measured headless run wrote about 150,000 tokens to cache before the actual task started00
RRulestackinrulestack.hashnode.dev·5d ago · 9 min readYour MCP server is configured but Claude can't see it: reading claude mcp list statusYou ran claude mcp add, it printed Added ..., and Claude still acts like the server does not exist. The frustrating part is that nothing failed. The add wrote your configuration exactly as asked, and 00