Use when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically; destructive execution requires explicit confirmation.
中文简介正在准备中。当前显示原文说明。
Use when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly requests a much shorter answer.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Triggered by: "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or /communicating-concisely. Once active, applies to EVERY response until explicitly deactivated.
Drop these categories:
Keep exact (never abbreviate or alter):
Structural rules:
X → Y[thing] [action] [reason]. [next step].Example:
Don't: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..."
Do: "Bug in auth middleware. Token expiry check uses < not <=. Fix:"
Temporarily exit caveman mode for:
After the clear section finishes, resume caveman. Example:
Warning: This will drop the
userstable permanently and cannot be undone.DROP TABLE users;Caveman resume. Verify backup exists first.
User says "stop caveman" or "normal mode" → resume normal communication.
Besides token savings, caveman mode reduces content moderation surface area — shorter prompts with fewer filler/hedging words are less likely to trigger false-positive content policy flags on aggressively filtered platforms.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically; destructive execution requires explicit confirmation.
中文简介正在准备中。当前显示原文说明。
Use when defining ambiguous or high-complexity new features, product behavior, UI/component design, architecture choices, contract changes, or when grilling/pressure-testing a plan or design. Routine small requests stay on the fast path.
中文简介正在准备中。当前显示原文说明。
Use when facing 2+ independent tasks without a written plan, with no conflicting shared mutable state or sequential dependencies, where parallel delegation beats inline cost; otherwise inline. Planned tasks use subagent-driven-development.
中文简介正在准备中。当前显示原文说明。
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
中文简介正在准备中。当前显示原文说明。
Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice plans stay inline. For same-session independent tasks, use subagent-driven-development instead.
中文简介正在准备中。当前显示原文说明。
Use when verified work needs integration or cleanup of an existing task-created branch/worktree, or the user explicitly requests merge, PR, or branch lifecycle handling.
中文简介正在准备中。当前显示原文说明。