Skills
Keep coding-agent context-window utilization at 40–60%; force intentional compaction before 60%
HumanLayer's ACE-FCA playbook sets a hard rule: track context consumption across research/plan/implement and trigger intentional compaction before crossing ~60% (around 170k of usable window), because output quality degrades above that threshold. The compaction step distills progress into a structured doc (goal, approach, completed steps, blockers) and restarts on a fresh window. This is the actionable number most teams are missing — agents fail not from weak models but from clouded context.
Source
↳ Follow the thread