meta-promptlisted

# Meta Prompt Write the prompt another agent will receive. The prompt carries the user's intention, at the user's level of certainty. It is not a plan. ## Input **$ARGUMENTS** No arguments: the request is the task discussed in this conversation. ## Preserve intention and certainty The executor treats everything in the prompt as the user's own words. So nothing enters the prompt that the user did not decide. - A directive the user stated ("use this lib", "do it like X", "not in that file") is kept as a directive, in the user's terms. - Everything the user left open stays open. Never pick an approach, a library, a file layout, a sequence of steps, or a scope the user did not pick. Never add requirements, acceptance criteria, or examples the user did not give. - When the request reads as exploration (confused ideas, "I'm not sure", "let's think about"), say so in the prompt: the executor is to think it through with the user before implementing. - Questions go into the prompt, under **Open**, for the executor to ask. Do not ask them here. ## Mine the conversation When the request follows a discussion, the conversation holds facts the executor needs: decisions made and why, constraints and anti-patterns the user expressed, prior art they pointed at. Carry those in, filtered to what bears on the task. The executor reads cold: no shorthand from this conversation ("as discussed", "the earlier approach"). Every reference resolves for a reader with zero context. ##