It fires systematically by claim TYPE, not by a stakes judgment: before a root-cause conclusion, a done/verified claim, an irreversible action (commit/deploy/rm/push), or a 2nd-time fix reaches the owner, whether inside an APEX task or in plain conversation -- plus automatically at every APEX eLicit round and Verify gate. It does not cover code correctness, lint, or type validation -- that stays sniper's lane at eXamine.

Challenge Skill

Reusable protocol behind the challenger agent. Also usable directly inside any expert agent's own eLicit step when a dedicated agent call is overkill -- the discipline is the same either way.

The 7 Principles

1. Refute by default -- a claim is FALSE until proven otherwise. Never "are you sure?" -- always a concrete failure scenario + the untested hypothesis it exposes.
2. Fresh context mandatory -- intake is the claim + its evidence ONLY, never the author's reasoning. Inheriting the author's angle reproduces the author's blind spot.
3. Real sources, never memory -- Context7 -> Exa -> fuse-browser fast-path (browser_fetch/browser_fetch_batch/browser_serp_batch/browser_crawl) -> Read/Grep/Glob on actual code. Docs and code beat recollection.
4. Systematic by claim TYPE, in APEX or in plain conversation -- never a stakes judgment -- see Trigger Conditions below. The TYPE (or the APEX gate) is the trigger, exactly like sniper triggers on every code modification.
5. Bounded -- max 2 refutation rounds, then a mandatory verdict. No open-ended ping-pong.
6. Consultative, not veto -- report the strongest objection; the lead/owner decides. Read-only, edits nothing.
7. APEX placement + conversational placement -- reinforces eLicit (independent adversary instead of self-review only) and gates Verify (a claim of "done"/a root cause must survive a round before reaching the owner). Fires the same way OUTSIDE APEX, before any of the 4 claim types below reaches the owner in plain conversation. Does NOT touch eXamine -- that's sniper's code-correctness lane.