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:
- READ: Complete feedback without reacting
- UNDERSTAND: Restate requirement in own words (or ask)
- VERIFY: Check against codebase reality
- EVALUATE: Technically sound for THIS codebase?
- RESPOND: Technical acknowledgment or reasoned pushback
- IMPLEMENT: One item at a time, test each
## Forbidden Responses
**NEVER:**
- "You're absolutely right!" (performative)
- "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:**
Human: "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:
- Check: Technically correct for THIS codebase?
- Check: Breaks existing functionality?
- Check: Reason for current implementation?
- Check: Works on all platforms/versions?
- 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 human partner's prior decisions: Stop and discuss with human partner first
**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
**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:
- Clarify anything unclear FIRST
- Then implement in this order:
- Blocking issues (breaks, security)
- Simple fixes (typos, imports)
- Complex fixes (refactoring, logic)
- Test each fix individually
- 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 human partner's architectural decisions
**How to push back:**
- Use technical reasoning, not defensiveness
- Ask specific questions
- Reference working tests/code
- Involve 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]
NOT: "You're absolutely right!" "Great point!" "Thanks for catching that!" 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."
NOT: 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):**
Human: "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.
## The Bottom Line
**External feedback = suggestions to evaluate, not orders to follow.**
Verify. Question. Then implement.
No performative agreement. Technical rigor always.
## Iron Laws
1. **NEVER** implement feedback before verifying it is technically correct for this specific codebase — reviewer suggestions are proposals, not orders.
2. **ALWAYS** clarify every unclear item before implementing any — partial understanding of a multi-item review produces wrong implementations that compound each other.
3. **NEVER** write performative agreement ("great point!", "you're absolutely right!") — technical acknowledgment or corrected code is the only valid response.
4. **ALWAYS** implement fixes one item at a time with individual test verification — batch implementations without testing create cascading bugs.
5. **NEVER** implement a suggested feature that grep confirms is unused — YAGNI applies; unused code is technical debt disguised as improvement.
## Anti-Patterns
| Anti-Pattern | Why It Fails | Correct Approach |
| ------------------------------------------------ | --------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
| Implementing all feedback without verification | Reviewer may lack full context; suggestion may break existing functionality | Verify each item against codebase before implementing |
| Starting implementation with unclear items | Missing context on item 4 corrupts items 1-3 that depend on it | Clarify all unclear items first; implement nothing until all items are understood |
| Expressing gratitude for feedback | Performative responses waste tokens and add no technical value | Respond with the technical fact (what was wrong, what was fixed) or just the code change |
| Batch-implementing without testing | One wrong fix corrupts the entire batch; regressions become invisible | Implement and test each item individually; commit checkpoints after each |
| Adding suggested features without checking usage | Implements dead code that must be maintained forever | Grep for actual usage first; if unused, confirm removal is the right answer |
## Memory Protocol (MANDATORY)
**Before starting:**
Read `.claude/context/memory/learnings.md`
**After completing:**
- New pattern -> `.claude/context/memory/learnings.md`
- Issue found -> `.claude/context/memory/issues.md`
- Decision made -> `.claude/context/memory/decisions.md`
> ASSUME INTERRUPTION: If it's not in memory, it didn't happen.