code-investigator_skill

Overview

This skill performs a systematic, end-to-end investigation and audit of a codebase. It discovers features and entry points, runs parallel subagents to analyze security, dead code, architecture, errors, dependencies, and tests, and delivers a prioritized, actionable risk report. Use it to get a clear plan for immediate fixes and medium-term improvements.

How this skill works

First, it maps the project by identifying framework, modules, entry points, routes, dependencies, and configuration to produce a feature inventory. Next, it launches multiple parallel subagents, each with a focused checklist (security, dead code, architecture, error handling, dependencies, tests) that report findings with file paths, line numbers, and severity ratings. Finally, it synthesizes subagent outputs into a single prioritized report with remediation recommendations and sorting by criticality.

When to use it

• You want a full project health check before a release or handoff
• You need a prioritized list of security vulnerabilities and fixes
• You want to locate and safely remove dead or redundant code
• You need actionable dependency and license risk assessment
• You want a consolidated assessment of missing tests and error handling

Best practices

• Provide repository access and specify the primary entrypoints or build commands
• Allow the initial feature inventory review before running full investigations
• Choose optional subagents appropriate to the project (profiling, TS strictness, API contracts)
• Require file path and line number for every finding to enable quick triage
• Treat confirmed findings separate from potential concerns; never report unverified issues

Example use cases

• Pre-release audit to catch security and crash risks before shipping
• Onboarding: produce a feature inventory and risk map for new maintainers
• Refactoring sprint: identify dead code and coupling hot spots to reduce scope
• Open-source maintainers: surface vulnerable dependencies and license issues
• QA lead: get prioritized list of missing tests and critical unhandled errors