{"version":"2.1.302","anchor":"forkcontext-metrics-system-prompt-now-built-with-withclise","canonical_anchor":"forkcontext-metrics-system-prompt-now-built-with-withclise","heading":"Context measuring now builds the system prompt in a different way","tier":"internal","area":"Elsewhere","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.302\/e\/forkcontext-metrics-system-prompt-now-built-with-withclise","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.302","markdown":"### Context measuring now builds the system prompt in a different way\n\nThe part of Claude Code that measures what fills the context now assembles the system prompt differently\n\n**What**\n\nThe system prompt is the standing set of instructions Claude Code gives the model, and the context is everything the model can see at once. The part of Claude Code that analyses what fills the context now builds the system prompt from its base with the command-line sections added, instead of splitting it at a boundary and appending a further prompt.\n\n**Why**\n\nThis concerns how the system prompt is put together for measurement, and no visible effect has been identified.\n\n- Area: Elsewhere\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}