{"version":"2.1.284","anchor":"opusplan-model-arm-now-gets-the-compact-harness-system-pro","canonical_anchor":"opusplan-model-arm-now-gets-the-compact-harness-system-pro","heading":"The opusplan model setting now gets a much shorter system prompt","tier":"notice","area":"Models","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.284\/e\/opusplan-model-arm-now-gets-the-compact-harness-system-pro","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.284","markdown":"### The `opusplan` model setting now gets a much shorter system prompt\n\nWith `opusplan`, Claude Code now sends Claude a compact system prompt with a short Harness section and a condensed memory guide\n\n**Unclear.** Why `opusplan` switched to the short prompt is unclear; it may be because it now resolves to a different underlying model.\n\n**What**\n\nThe system prompt is the standing set of instructions Claude Code gives Claude at the start of every conversation. When you use the `opusplan` model setting, in the terminal or through the SDK, Claude now gets a short version of that prompt instead of the full one. Claude Code already had this short version; what changed is that `opusplan` now uses it.\n\nThe short prompt has:\n\n- A \"# Harness\" section.\n\n- One paragraph about risky actions.\n\n- A condensed \"# Memory\" section.\n\nThese long sections of the full prompt are gone for `opusplan`: \"Doing tasks\", \"Executing actions with care\", \"Tone and style\", \"Text output\", and the long guide to the types of memory Claude can save.\n\n**Why**\n\nThe shorter prompt no longer carries an explicit list of destructive actions to be careful with, and its memory guidance is much briefer. If you use `opusplan`, Claude's behaviour may shift as a result.\n\n- Area: Models\n- Names: `opusplan`\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}