A Hacker News post said Claude Code burns 15 to 20 percent of tokens on a status line. The status line is innocent. I reproduced the real culprit, an agent summary, and measured what it costs.
Red Hat benchmarked Jev against 8 other guardrail models and found a local classifier beats it on speed by 6x. I tried to reproduce that result myself, on my own task.
The same classification task, run through Jev and Gemini 3.8 Flash with real API calls: identical accuracy, four to five times the latency, eight to thirty-four times the cost.
DeepSeek's DSec runs 380,000 concurrent AI-agent sandboxes a day. Not by caching one big image, but by admitting most of a sandbox can never be reused, and building around that instead.
Gambit Security recovered the staging server behind a three-agent breach of 27 companies. The same ungated pipeline destroyed its own stolen data — the exact failure mode this blog already mapped.
I gave one reviewer agent nothing and another a 210-word handoff note. Cognition says blind works better. The one with the note caught the bug that actually mattered.
Two subagents build the two halves of a receipt module in total isolation. One half won't compile. The fixed version compiles, runs, looks correct — and is silently wrong by a cent.
Two subagents with identical toolboxes and different system prompts boot 104 tokens apart. Add four tools and the gap is 17,252. The boot bill is the toolbox, and two tools are most of it.
A subagent that runs one wc -w burns 34,172 tokens. Split the work across five and the bill is 4.85x for a 1.79x speedup - the multiplier is a boot sequence, paid again every time you fan out.
A multi-turn agent replays its entire history on every request. Caching, context editing and compaction each attack a different part of that bill — and one of them, at its defaults, made it worse.
Cardinality does not creep up on you — it multiplies. Here is the arithmetic behind an exploding metrics bill, the four places the multiplication hides, and what actually shrinks it.