Skill Claude CodeCodex
Use when about to return a non-measurable output — writing, proposals, plans, explanations, designs, drafts, or any artifact whose quality is judged rather than tested. Also use when the user says "second pass this", "grade this", "is this good enough?", "self-judge", "iterate on this". Do NOT use for measurable…
Agent
Internal subagent for the Second Pass skill. Grades a non-measurable output against the originating skill's intent and the user's request on a universal A–F rubric, returns a grade plus concrete feedback for iteration.
Command
Toggle Second Pass re-judge after revision. true = verify lift in a loop (more tokens, more confidence). false = trust judge's feedback, ship after one revision (default, cheaper).
Command
Set the Second Pass iteration cap — the max number of revision attempts before the skill delivers the best attempt and stops. Accepts a positive integer.
Command
Set Second Pass to lenient mode — passing grade C, iteration cap 2, confirm revisions off. For quick drafts where speed beats polish.
Command
Set the Second Pass passing grade. Any output graded below this bar triggers a revision loop. Accepts A, B, C, D, or F.
Command
Reset Second Pass settings to defaults — passing grade B, iteration cap 3, confirm revisions off. Overwrites any custom config.
Command
Set Second Pass to strict mode — passing grade A, iteration cap 5, confirm revisions on. For high-stakes artifacts (client proposals, public-facing copy).