ijfw-receiving-review

# IJFW Receiving Review -- technical rigor over performance Paired with `ijfw-review` (reviewer side). This is the implementer side: how to react to findings from `ijfw-review`, `ijfw-cross-audit`, a human PR reviewer, a book editor, a design critic, or any other source -- without two failure modes. **Failure mode A: blind agreement.** "You're absolutely right!" then implement. The finding was never verified. Half the time the reviewer was wrong, the cited line moved, or the suggested fix breaks an invariant they did not know about. You now own a regression. **Failure mode B: performative pushback.** "I disagree, this is fine." No technical specifics, no citation, no evidence. Reviewer pushes back harder. You either cave (back to A) or dig in (the regression ships anyway). The rule: every finding gets ONE of three legitimate replies, and each reply has an evidence bar. --- ## 1. Three legitimate replies to a finding Pick ONE per finding. Never "I'll think about it" -- that is silent deferral and rots the review thread. - **Agree-and-fix** -- reproduce the finding, accept it, change the code, link the commit. - **Disagree-with-reason** -- cite the file, the line, the contract, the test, or the invariant that makes the finding wrong. No vibes. - **Need-more-info** -- ask ONE specific question. Not "can you explain?" Instead: "you flagged L42 as a null deref -- is the concern the early-return path on L38 or the catch block on L51?" If you cannot pick one within 60 secon...