- Home
- Skills
- Code Quality & Review
- legacy-system-archaeologist
Works with the AI Agents you already use
Legacy System Archaeologist
Reconstruct architecture and map risks in inherited legacy codebases with evidence-based auditing and migration plans.
Free
legacy-system-archaeologist
Example session with this skill installed
I've inherited this messy monolith and need to know what's safe to touch. Analyze the codebase, check the billing logic, and give me a risk assessment and migration plan.
- Read your context and instructions
- Compiled the legacy-system-archaeologist
System Health: CRITICAL
Risk Register
- /app/services/billing_engine.rb: BLACK (High fan-in: 42, Git churn: high, 0 tests)
- /lib/legacy_utils.js: RED (Dead code candidate, but dynamic dispatch possible)
Plan: Implement 5 characterization tests on billing_engine before refactoring.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
The Legacy System Archaeologist is a specialized toolkit for developers who have inherited "black box" codebases. It performs deep structural analysis to reconstruct system architecture, map dependencies, and identify high-risk modules before you write a single line of code.
Why use this skill
Modernizing legacy systems is dangerous because the "why" and "how" are often lost to time. While a standard AI might give you generic refactoring advice, this skill uses a rigorous 6-phase protocol—Inventory, Dependency Mapping, Risk Scoring, Dead Code Analysis, Architecture Reconstruction, and Strategy Reporting—to provide evidence-based insights.
It goes beyond simple prompting by using dedicated scripts to calculate "fan-in" (coupling), git churn (instability), and risk classifications. You get a professional-grade audit that identifies "Black Zone" files (like auth or payments) that no agent or human should touch without characterization tests.
Supported tools
- Languages: Multi-framework support (Rails, Laravel, Django, Node, Spring, .NET)
- Analysis Scripts: Python-based dependency graphers and risk scorers
- Context: Git history analysis and static code analysis
The Result
You receive a structured documentation suite including an Executive Summary for stakeholders, a full System Map, a file-level Risk Register, and a phased Migration Plan based on the Strangler Fig pattern.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.
Scope: static only, no runtime, no logs, no DB, results hint not truth, human check needed
Language: full Python JS TS Ruby, weak Kotlin Rust Scala C#, frameworks mostly Rails Django Node, can misread
Dependencies: Python top-level only, JS/TS weak on dynamic/aliases, cycles shallow
Dead code: text match only, not real proof, misses dynamic, queues, webhooks, cron
Risk: keyword based, false hits, false misses, not security audit
Repo: needs full repo, Git stats need full .git, ZIP no churn
Performance: big repo slow, full scans heavy
Non-goals: not code review, not testing, not security, not compliance
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
5 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 6 months ago
- Free with an Agensi account