Start with the person.
Identify who benefits, whether the request is the real problem, and whether a smaller answer would serve the goal better.
A portable judgment layer for tool-calling agents
Purpose Check helps capable agents notice when execution is drifting away from the person, outcome, or constraint that matters.
Purpose Check gives an agent a simple choice architecture. It knows when to stay quiet, when to state an assumption, and when one question is worth the interruption.
A clear, low-risk task gets a brief purpose check and no question. The work should feel fast because the stakes are low.
The purpose anchor carries the original intent from the first decision to the final handoff. It is one sentence naming who this is for and what gets better for them.
Identify who benefits, whether the request is the real problem, and whether a smaller answer would serve the goal better.
Define an outcome a non-expert could verify. Name the decision or action the output supports.
Compare meaningful choices against the purpose anchor. Surface only tradeoffs that reach the user or change the stakes.
Check for drift, misplaced quality effort, and unresolved consequential assumptions before delivery.
Keep it concrete enough to disagree with. A purpose anchor is a working constraint, not a mission statement.
Who is this for, and what gets better for them?
A returning user gets back into their account in under ten seconds.
Five models. Four revisions. The review trail stays in the repository because the corrections are part of the work.
Strong concept. Broad trigger, missing gates, weak completion checks.
Better structure, but the first score rewarded section presence over coherence.
Found the producer-consumer bug: Stage 3 needed an artifact Stage 1 did not always create.
Behavioral contracts resolved. The source is ready for any agent harness.
Read the complete skill, inspect the review trail, and give your agent a judgment layer that knows when to ask and when to move.