agents

I'm testing whether the rules and tools from my agent operator can do more useful work as a shared kit. The design moves coordination into project sessions; the review explains why that's worth trying, where the evidence is weak, and what the seven-day trial must show.

I applied Jon McNeill's five-step sequence from The Algorithm to six recurring Command jobs. The strongest opened 31 remediation pull requests in 30 days, and 29 merged, showing how accurate automation becomes finished work.

I spent about three weeks making the 38 unattended jobs in my operator's registry write down their setpoint, sensor, error signal, and actuator, plus whether they can tell a failed measurement from a healthy reading. Sixteen declared they aren't control loops at all, and only two of the rest close the loop: they act on the world and then check that the action worked.

How I use local Codex and Claude Code session logs to recover decisions, continue unfinished work, monitor active tasks, and turn patterns across sessions into handoffs, reports, and plans.

I built Karpathy's LLM wiki pattern into Command, my Claude Code operator: 134 provenance-tagged pages, a grep gate that blocks fabricated quotes, a nightly digest pipeline that was reset after a cheap model wrote a wrong verdict into it, and a human-gated publish wall.

The key design decisions in Command, my autonomous Claude Code operator: why the watcher is deterministic and free, why it authors per-repo config instead of loading it, why every fix carries a pre-registered success criterion, and what I want to see from it next.

Prose design specs drift the moment nobody's looking, and coding agents now read them as ground truth. The two-stage CI guard in chat-arch treats every palette-table row as a falsifiable claim: what it catches, the contrast bug that earned its own token, and the geometry drift it sailed right past.

Anthropic's latest harness research reveals two underappreciated patterns: why agents can't evaluate their own work (and what to do about it), and why you should be actively removing complexity from your agent harnesses as models improve.

Subagents, skills, CLAUDE.md orchestration, headless execution, and state management patterns for Claude Code multi-agent systems. 50 claims verified against official Anthropic docs.

How I built ShopForge, a production AI agent with three-tier memory, Bayesian confidence scoring, and skill evolution, and what 10 days of real Etsy operations taught me about self-improving systems.