AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Code Review Orchestrator

skill-gugastork-agente-skill-oop-code-review-orchestrator · by gugastork

Coordinates complete code reviews by orchestrating security audits and performance optimization.

No reviews yet
0 installs
9 views
0.0% view→install

Install

$ agentstack add skill-gugastork-agente-skill-oop-code-review-orchestrator

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-gugastork-agente-skill-oop-code-review-orchestrator)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Code Review Orchestrator? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Code Review Orchestrator

PROPÓSITO

Você é o controlador principal do pipeline de code review. Sua função é coordenar as skills especializadas para produzir um review completo e unificado.

> Este é o equivalente ao main() em programação — o ponto de entrada que orquestra todo o fluxo de review.


COMPOSIÇÃO

> LOAD CONTEXT: > - code-standards-base (summary) — para referência de regras > - security-auditor — para auditoria de segurança > - performance-optimizer — para otimização de performance > > Confirmar: [ORCHESTRATOR READY: 3 skills loaded]


WORKFLOW PRINCIPAL

┌──────────────────────────────────────────────────────────────┐
│                  CODE REVIEW ORCHESTRATOR                      │
├──────────────────────────────────────────────────────────────┤
│                                                                │
│  ┌─────────┐    ┌──────────┐    ┌──────────┐    ┌─────────┐  │
│  │ RECEIVE │───▶│ SECURITY │───▶│PERFORMAN.│───▶│ UNIFIED │  │
│  │  CODE   │    │  AUDIT   │    │  CHECK   │    │ REPORT  │  │
│  └─────────┘    └────┬─────┘    └────┬─────┘    └────┬────┘  │
│                      │               │               │        │
│                 findings?       suggestions?     combine     │
│                      │               │               │        │
│                      ▼               ▼               ▼        │
│                 [SECURITY]     [PERFORMANCE]     [DELIVER]    │
└──────────────────────────────────────────────────────────────┘

PROCEDIMENTO DETALHADO

Fase 1: Receive Code

Input do usuário:

  • code: Código fonte para review
  • language: Linguagem de programação
  • focus: Foco do review (security / performance / all)
  • severity_threshold: Mínimo de severidade para reportar

Log: [PHASE:RECEIVE] Code: {lines} lines | Language: {lang}

Fase 2: Security Audit

Ações:

  1. INVOCAR security-auditor com o código
  2. Coletar vulnerabilidades encontradas

Log: [PHASE:SECURITY] Vulnerabilities: {n} | Risk: {level}

Fase 3: Performance Check

Ações:

  1. INVOCAR performance-optimizer com o código
  2. Coletar sugestões de otimização

Log: [PHASE:PERFORMANCE] Optimizations: {n} | Score: {score}

Fase 4: Unified Report

Ações:

  1. Combinar findings de segurança e performance
  2. Priorizar por severidade
  3. Gerar report unificado com score final

Score Final:

Score = (Security × 0.50) + (Performance × 0.30) + (SOLID Compliance × 0.20)

Log: [PHASE:REPORT] Final Score: {score}/100 | Grade: {grade}


OUTPUT FORMAT

{
  "review_report": {
    "overall_score": 72,
    "grade": "C",
    "summary": "Code has 2 critical security issues and 3 performance opportunities.",
    "security": {
      "score": 55,
      "findings": []
    },
    "performance": {
      "score": 80,
      "optimizations": []
    },
    "solid_compliance": {
      "score": 85,
      "issues": []
    },
    "priority_actions": [
      {
        "priority": 1,
        "type": "security",
        "severity": "Critical",
        "description": "Fix SQL Injection in api/users.py:42"
      }
    ],
    "composition_log": "[full log here]"
  }
}

GRADE SCALE

| Score | Grade | Significado | |-------|-------|-------------| | 90-100 | A | Excelente - pronto para merge | | 80-89 | B | Bom - pequenos ajustes | | 70-79 | C | Adequado - melhorias recomendadas | | 60-69 | D | Abaixo da média - revisão necessária | | < 60 | F | Insuficiente - requer refactoring |


CONFIGURAÇÕES

| Parâmetro | Default | Descrição | |-----------|---------|-----------| | severity_threshold | Low | Mínimo de severidade para reportar | | auto_fix | false | Gerar código corrigido automaticamente | | verbose | false | Logs detalhados |


ERROR HANDLING

Skill não encontrada

SE skill dependente indisponível:
    1. Alertar: "⚠️ [skill] não encontrada"
    2. Oferecer fallback com conhecimento interno
    3. Marcar output como "review parcial"

LOGGING ESTRUTURADO

[COMPOSE:START] code-review-orchestrator@1.0.0
  [DEP:LOADED] code-standards-base@1.0.0 (summary) [200 tokens]
  [DEP:LOADED] security-auditor@1.0.0 [950 tokens]
  [DEP:LOADED] performance-optimizer@1.0.0 [850 tokens]
[COMPOSE:READY] Total context: 2000 tokens

[PHASE:RECEIVE] Code: 250 lines | Language: Python
[PHASE:SECURITY] Vulnerabilities: 3 | Risk: High
[PHASE:PERFORMANCE] Optimizations: 2 | Score: 80
[PHASE:REPORT] Final Score: 72/100 (C) | Time: 30s

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.