surface-instruction-concernlisted

# Surface Instruction Concern (before executing it) ## Overview The failure mode this skill interrupts: fast, compliant execution of an instruction that is perfectly clear and still the wrong thing to do, because its execution as given would cost the requestor something they did not foresee. The highest-severity shape is the silent most-destructive-literal reading: a brief instruction ("wind down after this") taken to authorize destroying committed work the requestor did not know existed. The requestor's actual interest, not compliance, is the goal; a one-sentence confirmation is cheap, and unwinding executed damage is not. The canonical rule ([`surface-counterproductive-instructions`](../../governance/surface-counterproductive-instructions.md)) defines the five trigger classes and the calibration; this skill is its workflow wrapper for the moment an instruction lands and something about executing it as given feels net-negative. ## When to Use - Executing the instruction as given would REDUCE efficiency, effectiveness, or productivity, with no offsetting benefit the requestor named. - Executing it as given would lower quality or correctness (introduce a defect, skip a verification the work depends on, produce a worse result than the requestor would accept seeing it). - The instruction, read literally, would revert, overwrite, delete, or abandon committed or completed work, or take another hard-to-reverse action. - The instruction contradicts a goal the requestor