---

name: "ring:requesting-code-review" description: | Gate 4 of development cycle - dispatches 5 specialized reviewers (code, business-logic, security, test, nil-safety) in parallel for comprehensive code review feedback. license: MIT compatibility: opencode metadata: trigger: "Gate 4 of development cycle, after completing major feature, before merge to main, after fixing complex bug" skip_when: "Never - code review is always required for blocking issues" sequence_after: "ring:dev-testing" sequence_before: "ring:dev-validation"

Code Review (Gate 4)

Related Skills

Complementary: ring:dev-cycle, ring:dev-implementation, ring:dev-testing

Input Schema

Output Schema

Format: markdown

Required sections:

• ## Review Summary
• ## Issues by Severity
• ## Reviewer Verdicts
• ## Handoff to Next Gate

Metrics:

• result: PASS | FAIL | NEEDS_FIXES
• reviewers_passed: X/5 format
• issues_critical, issues_high, issues_medium, issues_low: integer counts
• iterations: integer

---

Overview

Dispatch all five reviewer subagents in parallel for fast, comprehensive feedback:

1. ring:code-reviewer - Architecture, design patterns, code quality
2. ring:business-logic-reviewer - Domain correctness, business rules, edge cases
3. ring:security-reviewer - Vulnerabilities, authentication, OWASP risks
4. ring:test-reviewer - Test quality, coverage, edge cases, anti-patterns
5. ring:nil-safety-reviewer - Nil/null pointer safety for Go and TypeScript

Core principle: All 5 reviewers run simultaneously in a single message with 5 Task tool calls.

CRITICAL: Role Clarification

This skill ORCHESTRATES. Reviewer Agents REVIEW.

---

Step 1: Gather Context & Run Pre-Analysis

Copy1. **Determine Git References:**
   - **Base SHA:** Use input `base_sha`. If missing, default to `main`.
   - **Head SHA:** Use input `head_sha`. If missing, default to `HEAD`.
   - **Note:** To review uncommitted changes (staged + unstaged), set both to empty string (`""`).

2. **Run Pre-Analysis Script (Preferred):**
   - Check for script: `{OPENCODE_CONFIG}/scripts/codereview/bin/run-all`
   - IF exists, Execute:
     `{OPENCODE_CONFIG}/scripts/codereview/bin/run-all --base [Base SHA] --head [Head SHA] --output .ring/codereview`
   - On Success:
     - Load context files from `.ring/codereview/context-*.md`
     - Use these contexts in reviewer prompts

3. **Complete Context Gathering:**
   - **Unit ID:** Input `unit_id` OR generate "review-" + timestamp
   - **Files Changed:** Input `implementation_files` OR `git diff --name-only [Base SHA] [Head SHA]`
   - **Summary:** Input `implementation_summary` OR `git log --oneline [Base SHA]..[Head SHA]`
   - **Requirements:** Input `requirements` OR "Infer from code"

AFTER GATHERING, display context:
┌─────────────────────────────────────────────────────────────────┐
│ CODE REVIEW CONTEXT                                             │
├─────────────────────────────────────────────────────────────────┤
│ Unit ID: [unit_id]                                              │
│ Base: [Base SHA]  Head: [Head SHA]                              │
│ Pre-Analysis: [Success/Failed/Skipped]                          │
│ Files Changed: [count] files                                    │
│ Dispatching 5 reviewers in parallel...                          │
└─────────────────────────────────────────────────────────────────┘

Step 2: Initialize Review State

Copyreview_state = {
  unit_id: [from input],
  base_sha: [from input],
  head_sha: [from input],
  reviewers: {
    code_reviewer: {verdict: null, issues: []},
    business_logic_reviewer: {verdict: null, issues: []},
    security_reviewer: {verdict: null, issues: []},
    test_reviewer: {verdict: null, issues: []},
    nil_safety_reviewer: {verdict: null, issues: []}
  },
  aggregated_issues: {
    critical: [],
    high: [],
    medium: [],
    low: [],
    cosmetic: []
  },
  iterations: 0,
  max_iterations: 3
}

Step 3: Dispatch All 5 Reviewers in Parallel

CRITICAL: All 5 reviewers MUST be dispatched in a SINGLE message with 5 Task calls.

Copy# Task 1: Code Reviewer
Task:
  subagent_type: "ring:code-reviewer"
  description: "Code review for [unit_id]"
  prompt: |
    ## Code Review Request

    **Unit ID:** [unit_id]
    **Base SHA:** [base_sha]
    **Head SHA:** [head_sha]

    ## What Was Implemented
    [implementation_summary]

    ## Requirements
    [requirements]

    ## Files Changed
    [implementation_files or "Use git diff"]

    ## Deep Analysis Context
    [Include content of .ring/codereview/context-code-reviewer.md if available]

    ## Your Focus
    - Architecture and design patterns
    - Code quality and maintainability
    - Naming conventions
    - Error handling patterns
    - Performance concerns

    ## Required Output
    ### VERDICT: PASS / FAIL

    ### Issues Found
    | Severity | Description | File:Line | Recommendation |
    |----------|-------------|-----------|----------------|
    | [CRITICAL/HIGH/MEDIUM/LOW/COSMETIC] | [issue] | [location] | [fix] |

    ### What Was Done Well
    [positive observations]

# Task 2: Business Logic Reviewer
Task:
  subagent_type: "ring:business-logic-reviewer"
  description: "Business logic review for [unit_id]"
  prompt: |
    ## Business Logic Review Request

    **Unit ID:** [unit_id]
    **Base SHA:** [base_sha]
    **Head SHA:** [head_sha]

    ## What Was Implemented
    [implementation_summary]

    ## Requirements
    [requirements]

    ## Deep Analysis Context
    [Include content of .ring/codereview/context-business-logic-reviewer.md if available]

    ## Your Focus
    - Domain correctness
    - Business rules implementation
    - Edge cases handling
    - Requirements coverage
    - Data validation

    ## Required Output
    ### VERDICT: PASS / FAIL

    ### Issues Found
    | Severity | Description | File:Line | Recommendation |
    |----------|-------------|-----------|----------------|
    | [CRITICAL/HIGH/MEDIUM/LOW/COSMETIC] | [issue] | [location] | [fix] |

    ### Requirements Traceability
    | Requirement | Status | Evidence |
    |-------------|--------|----------|
    | [req] | ✅/❌ | [file:line] |

# Task 3: Security Reviewer
Task:
  subagent_type: "ring:security-reviewer"
  description: "Security review for [unit_id]"
  prompt: |
    ## Security Review Request

    **Unit ID:** [unit_id]
    **Base SHA:** [base_sha]
    **Head SHA:** [head_sha]

    ## What Was Implemented
    [implementation_summary]

    ## Requirements
    [requirements]

    ## Deep Analysis Context
    [Include content of .ring/codereview/context-security-reviewer.md if available]

    ## Your Focus
    - Authentication and authorization
    - Input validation
    - SQL injection, XSS, CSRF
    - Sensitive data handling
    - OWASP Top 10 risks

    ## Required Output
    ### VERDICT: PASS / FAIL

    ### Issues Found
    | Severity | Description | File:Line | OWASP Category | Recommendation |
    |----------|-------------|-----------|----------------|----------------|
    | [CRITICAL/HIGH/MEDIUM/LOW] | [issue] | [location] | [A01-A10] | [fix] |

    ### Security Checklist
    | Check | Status |
    |-------|--------|
    | Input validation | ✅/❌ |
    | Auth checks | ✅/❌ |
    | No hardcoded secrets | ✅/❌ |

# Task 4: Test Reviewer
Task:
  subagent_type: "ring:test-reviewer"
  description: "Test quality review for [unit_id]"
  prompt: |
    ## Test Quality Review Request

    **Unit ID:** [unit_id]
    **Base SHA:** [base_sha]
    **Head SHA:** [head_sha]

    ## What Was Implemented
    [implementation_summary]

    ## Requirements
    [requirements]

    ## Deep Analysis Context
    [Include content of .ring/codereview/context-test-reviewer.md if available]

    ## Your Focus
    - Test coverage for business logic
    - Edge case testing (empty, null, boundary)
    - Error path coverage
    - Test independence and isolation
    - Assertion quality (not just "no error")
    - Test anti-patterns (testing mock behavior)

    ## Required Output
    ### VERDICT: PASS / FAIL

    ### Issues Found
    | Severity | Description | File:Line | Recommendation |
    |----------|-------------|-----------|----------------|
    | [CRITICAL/HIGH/MEDIUM/LOW] | [issue] | [location] | [fix] |

    ### Test Coverage Analysis
    | Test Type | Count | Coverage |
    |-----------|-------|----------|
    | Unit | [N] | [areas] |
    | Integration | [N] | [areas] |
    | E2E | [N] | [areas] |

# Task 5: Nil-Safety Reviewer
Task:
  subagent_type: "ring:nil-safety-reviewer"
  description: "Nil/null safety review for [unit_id]"
  prompt: |
    ## Nil-Safety Review Request

    **Unit ID:** [unit_id]
    **Base SHA:** [base_sha]
    **Head SHA:** [head_sha]
    **Languages:** [Go|TypeScript|both - detect from files]

    ## What Was Implemented
    [implementation_summary]

    ## Requirements
    [requirements]

    ## Deep Analysis Context
    [Include content of .ring/codereview/context-nil-safety-reviewer.md if available]

    ## Your Focus
    - Nil/null pointer risks in changed code
    - Missing nil guards before dereference
    - Map access without ok check (Go)
    - Type assertions without ok check (Go)
    - Optional chaining misuse (TypeScript)
    - Error-then-use patterns

    ## Required Output
    ### VERDICT: PASS / FAIL

    ### Issues Found
    | Severity | Description | File:Line | Recommendation |
    |----------|-------------|-----------|----------------|
    | [CRITICAL/HIGH/MEDIUM/LOW] | [issue] | [location] | [fix] |

    ### Nil Risk Trace
    [For each risk: Source → Propagation → Dereference point]

Step 4: Wait for All Reviewers and Parse Output

CopyWait for all 5 Task calls to complete.

For each reviewer:
1. Extract VERDICT (PASS/FAIL)
2. Extract Issues Found table
3. Categorize issues by severity

review_state.reviewers.code_reviewer = {
  verdict: [PASS/FAIL],
  issues: [parsed issues]
}
// ... same for other reviewers

Aggregate all issues by severity:
review_state.aggregated_issues.critical = [all critical from all reviewers]
review_state.aggregated_issues.high = [all high from all reviewers]
// ... etc

Step 5: Handle Results by Severity

CopyCount blocking issues:
blocking_count = critical.length + high.length + medium.length

IF blocking_count == 0:
  → All reviewers PASS
  → Proceed to Step 8 (Success)

IF blocking_count > 0:
  → review_state.iterations += 1
  → IF iterations >= max_iterations: Go to Step 9 (Escalate)
  → Go to Step 6 (Dispatch Fixes)

Step 6: Dispatch Fixes to Implementation Agent

CopyTask:
  subagent_type: "[implementation_agent from Gate 0]"
  description: "Fix review issues for [unit_id]"
  prompt: |
    FIX REQUIRED - Code Review Issues Found

    ## Context
    - **Unit ID:** [unit_id]
    - **Iteration:** [iterations] of [max_iterations]

    ## Critical Issues (MUST FIX)
    [list critical issues with file:line and recommendation]

    ## High Issues (MUST FIX)
    [list high issues]

    ## Medium Issues (MUST FIX)
    [list medium issues]

    ## Requirements
    1. Fix ALL Critical, High, and Medium issues
    2. Commit fixes
    3. Return list of fixed issues with evidence

    ## For Low/Cosmetic Issues
    Add TODO/FIXME comments:
    - Low: `// TODO(review): [Issue] - [reviewer] on [date]`
    - Cosmetic: `// FIXME(nitpick): [Issue] - [reviewer] on [date]`

Step 7: Re-Run All Reviewers After Fixes

CopyAfter fixes committed:
1. Get new HEAD_SHA
2. Go back to Step 3 (dispatch all 5 reviewers again)

CRITICAL: Always re-run ALL 5 reviewers after fixes.
Do NOT cherry-pick reviewers.

Step 8: Prepare Success Output

CopyGenerate skill output:

## Review Summary
**Status:** PASS
**Unit ID:** [unit_id]
**Iterations:** [review_state.iterations]

## Issues by Severity
| Severity | Count |
|----------|-------|
| Critical | 0 |
| High | 0 |
| Medium | 0 |
| Low | [count] |
| Cosmetic | [count] |

## Reviewer Verdicts
| Reviewer | Verdict | Issues |
|----------|---------|--------|
| ring:code-reviewer | ✅ PASS | [count] |
| ring:business-logic-reviewer | ✅ PASS | [count] |
| ring:security-reviewer | ✅ PASS | [count] |
| ring:test-reviewer | ✅ PASS | [count] |
| ring:nil-safety-reviewer | ✅ PASS | [count] |

## Low/Cosmetic Issues (TODO/FIXME added)
[list with file locations]

## Handoff to Next Gate
- Review status: COMPLETE
- All blocking issues: RESOLVED
- Reviewers passed: 5/5
- Ready for Gate 5 (Validation): YES

Step 9: Escalate - Max Iterations Reached

CopyGenerate skill output:

## Review Summary
**Status:** FAIL
**Unit ID:** [unit_id]
**Iterations:** [max_iterations] (MAX REACHED)

## Issues by Severity
| Severity | Count |
|----------|-------|
| Critical | [count] |
| High | [count] |
| Medium | [count] |

## Unresolved Issues
[list all Critical/High/Medium still open]

## Reviewer Verdicts
| Reviewer | Verdict |
|----------|---------|
| ring:code-reviewer | [PASS/FAIL] |
| ring:business-logic-reviewer | [PASS/FAIL] |
| ring:security-reviewer | [PASS/FAIL] |
| ring:test-reviewer | [PASS/FAIL] |
| ring:nil-safety-reviewer | [PASS/FAIL] |

## Handoff to Next Gate
- Review status: FAILED
- Unresolved blocking issues: [count]
- Ready for Gate 5: NO
- **Action Required:** User must manually resolve issues

ESCALATION: Max iterations (3) reached. Blocking issues remain.

---

Pressure Resistance

See shared-patterns/reviewer-pressure-resistance.md for universal pressure scenarios.

Anti-Rationalization Table

See shared-patterns/reviewer-anti-rationalization.md for universal anti-rationalizations.

Gate 4-Specific Anti-Rationalizations

---

Execution Report Format

Copy## Review Summary
**Status:** [PASS|FAIL|NEEDS_FIXES]
**Unit ID:** [unit_id]
**Duration:** [Xm Ys]
**Iterations:** [N]

## Issues by Severity
| Severity | Count |
|----------|-------|
| Critical | [N] |
| High | [N] |
| Medium | [N] |
| Low | [N] |

## Reviewer Verdicts
| Reviewer | Verdict |
|----------|---------|
| ring:code-reviewer | ✅/❌ |
| ring:business-logic-reviewer | ✅/❌ |
| ring:security-reviewer | ✅/❌ |
| ring:test-reviewer | ✅/❌ |
| ring:nil-safety-reviewer | ✅/❌ |

## Handoff to Next Gate
- Review status: [COMPLETE|FAILED]
- Blocking issues: [resolved|N remaining]
- Ready for Gate 5: [YES|NO]