skills.rest
bacoco
bacocoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

sg-code-audit

Audit multi-language repositories with parallel agents and per-zone JSON results.

7|2|Updated Mar 24, 2026
Search Tags:#monitoring#static-analysis#parallel-agents#code-audit#automated-fixes#zone-splitting
One-click install
npx skills add https://github.com/bacoco/ShipGuard --skill sg-code-audit
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sg-code-audit
Source: https://github.com/bacoco/ShipGuard/tree/main/plugins/shipguard/skills/sg-code-audit
Command: npx skills add https://github.com/bacoco/ShipGuard --skill sg-code-audit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

ShipGuard's sg-code-audit automates the tedious and error-prone task of auditing a codebase for bugs, security issues, and integration mismatches by dispatching parallel agents that inspect, report, and optionally fix problems across the repository. It reduces manual review time, surfaces regressions introduced by changes, and produces structured, machine-readable findings for review and CI integration.

Core Features & Use Cases

  • Parallel, zone-based auditing: split a repo into non-overlapping zones and run concurrent agents to scale reviews across large codebases.
  • Modes and scopes: support quick, standard, deep, and paranoid modes plus diff-scoped or full-codebase runs for targeted or comprehensive audits.
  • Structured outputs & monitoring: write per-zone JSON results consumable by a review dashboard, and optionally serve a local monitor for live progress.
  • Model & verification strategies: choose model strategies, enforce severity/category schemas, and include multi-round depth passes for runtime and edge-case analysis.
  • Use case: run on a feature branch to audit only changed files and their importers, then send aggregated JSON to the visual review dashboard for triage and human validation.

Quick Start

Run /sg-code-audit in the conversation to scan the repository, produce zone JSON results, and optionally apply fixes.

Frequently Asked Questions about sg-code-audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate codebase audits to find and fix bugs across a multi-language repository?▼

Automated codebase audits use parallel, multi-round agents to inspect multi-language repositories, finding and fixing bugs across scoped diffs or full runs while enforcing strict zone boundaries and output schemas.

Can I run a static analysis audit on only the changed files in a feature branch?▼

Yes, static analysis audits support diff-scoped runs that target only changed files and their importers on a feature branch, allowing for targeted bug detection instead of scanning the entire codebase.

How do parallel agents audit large codebases without overlapping?▼

Parallel agents audit large codebases by splitting the repository into non-overlapping zones, running concurrent inspections per zone to scale reviews while enforcing strict zone boundaries.

What is the best way to integrate code audit results into a CI pipeline?▼

The best way to integrate code audit results into CI is by generating per-zone JSON outputs with enforced severity and category schemas, which are machine-readable for automated CI checks and downstream validation.

Does automated code auditing support different depths of analysis for runtime and edge cases?▼

Automated code auditing supports quick, standard, deep, and paranoid modes, utilizing multi-round depth passes and model selection strategies to analyze runtime behaviors and edge cases comprehensively.

How do I monitor live progress of a parallel codebase audit?▼

You can monitor live progress of a parallel codebase audit by serving an optional local monitor dashboard that tracks concurrent agent inspections and displays per-zone JSON results for real-time review.

Related Skills

Explore More Software Engineering Skills→
ssmleossmleo

govfolio-dispatching-parallel-agents

Dispatch independent tasks to parallel agents with non-overlapping state management.

Community
Intermediate
blueif16blueif16

create-command

Create slash command files and initialize plugin structure in Claude plugins.

Community
Basic
nguyenphpnguyenphp
41

lint-and-validate

Run linters, type checkers, and security audits across Node.js and Python projects.

Community
Intermediate
foutoucourfoutoucour

security

Orchestrate security assessments across code, infrastructure, auth, secrets, and pentest.

Community
Advanced