Your Agents Eat Your Subscription
Subscription-authenticated agents can share interactive usage allowances. Check authentication, current rate cards and spend-control semantics before budgeting automation.
Subscription-authenticated agents can share interactive usage allowances. Check authentication, current rate cards and spend-control semantics before budgeting automation.
claude agents and /agents are different products solving opposite problems, and the slash command stopped doing what every tutorial says. Five ways Claude Code runs more than one thing at once, what each really costs, and the one cleanup behaviour that will delete someone's work.
Claude marks supported text outputs with an invisible watermark. Detection offers conditional provenance evidence; code robustness and authorship require separate checks.
The most expensive code your agents write is clean, tested, documented and unnecessary. A working 2026 protocol for finding what to remove, before it hardens into architecture.
Harness, loop, graph, context engineering. Four terms everyone uses and almost nobody defines. Here is what each one means, which layer your system is actually failing at, and what it takes to get to something that ships work without you typing a prompt every time.
Steve Yegge spent six weeks building an agent harness that grew into something with law, offices, courts and a constitution. Then he wrote a second essay arguing the agents inside it are sentient persons. Four very different claims are stacked in there. Only some of them hold.
Anthropic shipped cross-session messaging as a convenience feature: stop re-explaining yourself in the other terminal. What actually shipped is an addressable peer network with its own threat model already written into the product, and the engineering worth reading is all in what a session refuses.
Agent cost depends on carried context, request frequency, caching, and authentication. A privacy-preserving engineering framework with explicitly hypothetical arithmetic, separate from measured billing or subscription allowances.
Automating PR-review handoffs through repository-state reconciliation while retaining human acceptance.
A source-level review of nine agent frameworks: what they mechanically do, the conventions they share, and the case for adopting their ideas in a custom setup.
Meta’s May 2026 display SDK preview expands development options. Consumer app availability, optical fit and useful recurring workflows still determine the value of these glasses.
AI can reduce the effort of reproducing some software features. A reassessment of competitive advantage through distribution, trust, operating knowledge and production requirements.