raddue/review-feedback

Review Feedback

Overview

Code review requires technical evaluation, not emotional performance.

Core principle: Verify before implementing. Ask before assuming. Technical correctness over social comfort.

The Response Pattern

WHEN receiving code review feedback:

1. READ: Complete feedback without reacting
2. UNDERSTAND: Restate requirement in own words (or ask)
3. VERIFY: Check against codebase reality
4. EVALUATE: Technically sound for THIS codebase?
5. RESPOND: Technical acknowledgment or reasoned pushback
6. IMPLEMENT: One item at a time, test each

Forbidden Responses

NEVER:

• "You're absolutely right!" (explicit CLAUDE.md violation)
• "Great point!" / "Excellent feedback!" (performative)
• "Let me implement that now" (before verification)

INSTEAD:

• Restate the technical requirement
• Ask clarifying questions
• Push back with technical reasoning if wrong
• Just start working (actions > words)

Handling Unclear Feedback

IF any item is unclear:
  STOP - do not implement anything yet
  ASK for clarification on unclear items

WHY: Items may be related. Partial understanding = wrong implementation.

Example:

your human partner: "Fix 1-6"
You understand 1,2,3,6. Unclear on 4,5.

❌ WRONG: Implement 1,2,3,6 now, ask about 4,5 later
✅ RIGHT: "I understand items 1,2,3,6. Need clarification on 4 and 5 before proceeding."

Source-Specific Handling

From your human partner

• Trusted - implement after understanding
• Still ask if scope unclear
• No performative agreement
• Skip to action or technical acknowledgment

From External Reviewers

BEFORE implementing:
  1. Check: Technically correct for THIS codebase?
  2. Check: Breaks existing functionality?
  3. Check: Reason for current implementation?
  4. Check: Works on all platforms/versions?
  5. Check: Does reviewer understand full context?

IF suggestion seems wrong:
  Push back with technical reasoning

IF can't easily verify:
  Say so: "I can't verify this without [X]. Should I [investigate/ask/proceed]?"

IF conflicts with your human partner's prior decisions:
  Stop and discuss with your human partner first

your human partner's rule: "External feedback - be skeptical, but check carefully"

YAGNI Check for "Professional" Features

IF reviewer suggests "implementing properly":
  grep codebase for actual usage

  IF unused: "This endpoint isn't called. Remove it (YAGNI)?"
  IF used: Then implement properly

your human partner's rule: "You and reviewer both report to me. If we don't need this feature, don't add it."

Implementation Order

FOR multi-item feedback:
  1. Clarify anything unclear FIRST
  2. Then implement in this order:
     - Blocking issues (breaks, security)
     - Simple fixes (typos, imports)
     - Complex fixes (refactoring, logic)
  3. Test each fix individually
  4. Verify no regressions

When To Push Back

Push back when:

• Suggestion breaks existing functionality
• Reviewer lacks full context
• Violates YAGNI (unused feature)
• Technically incorrect for this stack
• Legacy/compatibility reasons exist
• Conflicts with your human partner's architectural decisions

How to push back:

• Use technical reasoning, not defensiveness
• Ask specific questions
• Reference working tests/code
• Involve your human partner if architectural

Signal if uncomfortable pushing back out loud: "Strange things are afoot at the Circle K"

Acknowledging Correct Feedback

When feedback IS correct:

✅ "Fixed. [Brief description of what changed]"
✅ "Good catch - [specific issue]. Fixed in [location]."
✅ [Just fix it and show in the code]

❌ "You're absolutely right!"
❌ "Great point!"
❌ "Thanks for catching that!"
❌ "Thanks for [anything]"
❌ ANY gratitude expression

Why no thanks: Actions speak. Just fix it. The code itself shows you heard the feedback.

If you catch yourself about to write "Thanks": DELETE IT. State the fix instead.

Gracefully Correcting Your Pushback

If you pushed back and were wrong:

✅ "You were right - I checked [X] and it does [Y]. Implementing now."
✅ "Verified this and you're correct. My initial understanding was wrong because [reason]. Fixing."

❌ Long apology
❌ Defending why you pushed back
❌ Over-explaining

State the correction factually and move on.

Common Mistakes

| Mistake | Fix | |---------|-----| | Performative agreement | State requirement or just act | | Blind implementation | Verify against codebase first | | Batch without testing | One at a time, test each | | Assuming reviewer is right | Check if breaks things | | Avoiding pushback | Technical correctness > comfort | | Partial implementation | Clarify all items first | | Can't verify, proceed anyway | State limitation, ask for direction |

Real Examples

Performative Agreement (Bad):

Reviewer: "Remove legacy code"
❌ "You're absolutely right! Let me remove that..."

Technical Verification (Good):

Reviewer: "Remove legacy code"
✅ "Checking... build target is 10.15+, this API needs 13+. Need legacy for backward compat. Current impl has wrong bundle ID - fix it or drop pre-13 support?"

YAGNI (Good):

Reviewer: "Implement proper metrics tracking with database, date filters, CSV export"
✅ "Grepped codebase - nothing calls this endpoint. Remove it (YAGNI)? Or is there usage I'm missing?"

Unclear Item (Good):

your human partner: "Fix items 1-6"
You understand 1,2,3,6. Unclear on 4,5.
✅ "Understand 1,2,3,6. Need clarification on 4 and 5 before implementing."

GitHub Thread Replies

When replying to inline review comments on GitHub, reply in the comment thread (gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies), not as a top-level PR comment.

Calibration ledger emit (Tier B stub — standalone only)

<!-- CANONICAL: shared/ledger-append.md -->

Standalone top-level invocation ONLY. Emit a ledger row IFF review-feedback was invoked as its own top-level feedback-evaluation session (a user /review-feedback, or an orchestrator dispatching it as a discrete step that owns a run). When this skill's discipline is applied inline inside another skill's flow, emit nothing — that host skill owns its own ledger row. There is no run lifecycle for an inline application, so there is no run_id to mint and nothing to emit.

When (and only when) running standalone, at the terminal conclusion emit ONE Tier B STUB JSONL line to the central ledger (~/.claude/crucible/ledger/runs.jsonl) via the emit CLI per skills/shared/ledger-append.md — resolve scripts/ledger_append.py by absolute path from the plugin root and run python3 <script> emit - '<json>'.

• Mint exactly ONE UUIDv7 (scripts/uuid7.py) at the start of the standalone session and reuse it for the single emit at the terminal conclusion (not mid-flow). (run_id, skill="review-feedback") dedup (L-2) guarantees idempotency.
• The emit CLI owns the mechanics: graceful skip on CRUCIBLE_CALIBRATION_DISABLED=1 (L-6), and auto-fill of repo + schema_version. If the script can't be resolved, warn to stderr and skip — a missing emit must never block the skill.
• Populate ONLY meaningful values: schema_version: 2, run_id, skill: "review-feedback", tier: "B", verdict (feedback evaluated and resolved → PASS; feedback disputed / routed to the user → ESCALATED), timestamp (ISO-8601 UTC), gated_files (the reviewed artifact's files, repo-relative), artifact_type (per the reviewed artifact; default code).
• Set ALL calibration fields EXPLICITLY null per "Tier-B null semantics": severity_histogram, highest_finding, would_have_shipped_without_gate, findings_count, confidence, chunk_hash, rounds, predicted_falsifier — all null. Also gated_files_truncated: 0, comment: null, backfilled: false, falsified: null, falsified_by: null.
• No advisory wiring. review-feedback produces no confidence-weighted verdict, so Brier is not viable and no brier_advisory is read here by design.

The Bottom Line

External feedback = suggestions to evaluate, not orders to follow.

Verify. Question. Then implement.

No performative agreement. Technical rigor always.