Real Skill packageSource verifiedClawHub registry

Code Review Auditor

Review code for bugs, security, architecture, smells, patterns, performance, tests, and refactor plans

Identity and source

Publisher attributionCarine Bertagnolli Bathagliniregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 58% rule confidence
Package forminstruction with code24 recorded files
Canonical sourceClawHub registryclawhub:cbbathaglini:code-review-auditor
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/5/2026.claude/skills/code-review-auditor

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/5/2026.agents/skills/code-review-auditor

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/5/2026skills/code-review-auditor

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @cbbathaglini/code-review-auditor
clawhub inspect @cbbathaglini/code-review-auditor --version 1.0.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
24 / 24 inspected as text
Checked
9/5/2026, 4:26:11 AM
Scanner
0.1.3
Policy
1.0.3
4 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
1 dependency and API indicators
  • api: clawhub.ai
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/4/2026, 6:13:34 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:cb1a3ef04f386391bb572da28fbb7d17afd1a407309de6450bdc35e61ba8aef6
Show up to 24 recorded paths
  • agents/openai.yaml
  • README.md
  • references/refactor-planning.md
  • references/reporting-examples.md
  • references/review-process.md
  • rules/categories.md
  • rules/overengineering.md
  • rules/scoring.md
  • scripts/create_review_run.py
  • skill-card.md
  • SKILL.md
  • stacks/database.md
  • stacks/java-spring.md
  • stacks/kafka.md
  • stacks/kotlin.md
  • stacks/node-typescript.md
  • stacks/react.md
  • stacks/swift.md
  • templates/finding.md
  • templates/output-structure.md
  • templates/refactoring-plan.md
  • templates/score.json
  • templates/summary.md
  • workflows/modes.md

Source changelog

Initial release of code-review-auditor. - Provides automated codebase reviews for bugs, security, architecture/SOLID, code smells, justified design patterns, anti-patterns, performance, observability, testability, hotspots, and refactoring planning. - Analysis modes never change project files; plans must be proposed and approved before implementation. - Supports multiple review modes: complete, diff, security, architecture, smells, patterns, performance, tests, hotspots, explain, fix, refactor, and challenge. - All results are output to a timestamped local review folder with structured review artifacts including findings, recommendations, and refactoring plans. - Each finding follows a rigorous contract with evidence, severity, impact, and recommendations. - Analysis is guided by stack- and category-specific rules and conventions.