alfredolopez80/code-reviewer
.claude/skills/code-reviewer/SKILL.md
Automated code review using official Claude Code plugin with parallel agents. Integrates ralph-security for OWASP validation and ralph-frontend for accessibility checks. Uses LSP for efficient code navigation.
$ install --global
skillsauthnpx skillsauth add alfredolopez80/multi-agent-ralph-loop code-reviewerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 15, 2026, 6:06 PM18.1s1 file scanned
SKILL.md
- # VERSION:
- 3.0.0
- name:
- code-reviewer
- description:
- Automated code review using official Claude Code plugin with parallel agents. Integrates ralph-security for OWASP validation and ralph-frontend for accessibility checks. Uses LSP for efficient code navigation.
- allowed-tools:
- LSP,Read,Write,Bash,Glob,Grep
Code Reviewer (Official Plugin)
Integrates the official Claude Code code-review plugin.
v2.88 Key Changes (MODEL-AGNOSTIC)
- Model-agnostic: Uses model configured in
~/.claude/settings.jsonor CLI/env vars - No flags required: Works with the configured default model
- Flexible: Works with GLM-5, Claude, Minimax, or any configured model
- Settings-driven: Model selection via
ANTHROPIC_DEFAULT_*_MODELenv vars
Quick Start
/code-review # Review current changes
/code-review --comment # Post review as PR comment
Architecture
4 parallel agents with confidence scoring (≥80):
- Agent #1: CLAUDE.md compliance
- Agent #2: CLAUDE.md compliance (redundancy)
- Agent #3: Bug detection (changes only)
- Agent #4: Git blame/history analysis
Features
- Multi-agent parallel review
- Confidence-based filtering
- Auto-skip closed/draft/trivial PRs
- Direct GitHub code links
Integration
Official plugin: ~/.claude-sneakpeek/zai/config/plugins/cache/anthropics/code-review/
Author: Boris Cherny ([email protected]) Version: 1.0.0
Agent Teams Integration (v2.88)
Optimal Scenario: Pure Custom Subagents
This skill uses Pure Custom Subagents (no Agent Teams) for focused code review operations.
Why Scenario B for Code Review
- Native multi-agent: Already uses 4 parallel agents via official plugin
- Read-only operation: Review should not modify code (tool restrictions critical)
- No coordination needed: Analysis is independent per file/PR
- Faster execution: Direct spawn avoids team creation overhead
Configuration
- No TeamCreate: Official plugin already handles parallelism
- Direct Task: Spawn ralph-reviewer for additional analysis if needed
- Tool Restrictions: Review agents restricted to Read/Grep/Glob (no Write/Edit)
- Model Inheritance: Use model configured in settings.json
Workflow Pattern
# Official plugin runs 4 parallel agents natively
/code-review → Plugin spawns 4 agents with confidence scoring
# For extended analysis (optional):
Task(subagent_type="ralph-reviewer", prompt="Deep analysis of specific file...")
→ Agent executes with restricted tools
→ Returns detailed findings
→ Complete
Tool Restrictions for Safety
| Agent | Allowed Tools | Purpose |
|-------|---------------|---------|
| ralph-reviewer | Read, Grep, Glob | Analysis only (no modifications) |
| ralph-researcher | Read, Grep, Glob | Context lookup only |
When NOT to Use Agent Teams
- Official plugin already provides parallel review
- Read-only analysis doesn't need team coordination
- Tool restrictions prevent accidental changes more effectively than teams
- When review is a one-shot operation (not multi-phase workflow)
Action Reporting (v2.93.0)
Esta skill genera reportes automáticos completos para trazabilidad:
Reporte Automático
Cuando esta skill completa, se genera automáticamente:
- En la conversación de Claude: Resultados visibles
- En el repositorio:
docs/actions/code-reviewer/{timestamp}.md - Metadatos JSON:
.claude/metadata/actions/code-reviewer/{timestamp}.json
Contenido del Reporte
Cada reporte incluye:
- ✅ Summary: Descripción de la tarea ejecutada
- ✅ Execution Details: Duración, iteraciones, archivos modificados
- ✅ Results: Errores encontrados, recomendaciones
- ✅ Next Steps: Próximas acciones sugeridas
Ver Reportes Anteriores
# Listar todos los reportes de esta skill
ls -lt docs/actions/code-reviewer/
# Ver el reporte más reciente
cat $(ls -t docs/actions/code-reviewer/*.md | head -1)
# Buscar reportes fallidos
grep -l "Status: FAILED" docs/actions/code-reviewer/*.md
Generación Manual (Opcional)
source .claude/lib/action-report-lib.sh
start_action_report "code-reviewer" "Task description"
# ... ejecución ...
complete_action_report "success" "Summary" "Recommendations"
Referencias del Sistema
- Action Reports System - Documentación completa
- action-report-lib.sh - Librería helper
- action-report-generator.sh - Generador
Related Skills
alfredolopez80/vault
development
VerifiedTrustedCommunity
Living knowledge base management. Actions: search (query vault), save (store learning), index (update indices), compile (raw->wiki->rules graduation), init (create vault structure). Follows Karpathy pipeline: ingest->compile->query. Use when: (1) searching accumulated knowledge, (2) saving learnings, (3) compiling raw notes into wiki, (4) initializing a new vault. Triggers: /vault, 'vault search', 'knowledge base', 'save learning'.
121SKILL.mdUpdated Apr 15, 2026
alfredolopez80/spec
testing
VerifiedTrustedCommunity
Produce a verifiable technical specification before coding. 6 mandatory sections: Interfaces, Behaviors, Invariants (from Aristotle Phase 2), File Plan, Test Plan, Exit Criteria (executable bash commands + expected results). Use when: (1) before implementing features with complexity > 4, (2) as Step 1.5 in orchestrator workflow, (3) when requirements need formalization. Triggers: /spec, 'create spec', 'write specification', 'technical spec'.
121SKILL.mdUpdated Apr 15, 2026
alfredolopez80/ship
testing
VerifiedTrustedCommunity
Pre-launch shipping checklist orchestrating /gates, /security, /browser-test, /perf. Ensures nothing ships without passing all quality checks. Use when: (1) before deploying, (2) before merging to main, (3) before release. Triggers: /ship, 'ship it', 'ready to deploy', 'pre-launch check'.
121SKILL.mdUpdated Apr 15, 2026
alfredolopez80/perf
development
VerifiedTrustedCommunity
Performance optimization skill. Core Web Vitals via Lighthouse, bundle size analysis, metrics tracking over time. Use when: (1) optimizing frontend performance, (2) analyzing bundle size, (3) tracking metrics regression. Triggers: /perf, 'performance audit', 'core web vitals', 'bundle size'.
121SKILL.mdUpdated Apr 15, 2026