legacy-modernizer

An agent skill by Jeffallan, from Jeffallan/claude-skills. Tags: api, automation, developer-tools, documentation, migration, strategy.

What it does

Designs incremental migration strategies, identifies service boundaries, produces dependency maps and migration roadmaps, and generates API facade designs for aging codebases. Use when modernizing legacy systems, implementing strangler fig pattern or branch by abstraction, decomposing monoliths, upgrading frameworks or languages, or reducing technical debt without disrupting business operations.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add Jeffallan/claude-skills --skill legacy-modernizer

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/Jeffallan/claude-skills
cp -r claude-skills/skills/legacy-modernizer ~/.claude/skills/legacy-modernizer

Safety box score

Grade B, low risk: 18 of 100 risk points, rated 2026-10-17. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is mostly an architecture and migration-planning guide, but it includes runnable analysis scripts and code templates that read the whole repo, inspect git history, write generated artifacts, and route live traffic during incremental rollouts. The main risks are bounded execution/network/file writes plus the inherent blast radius of migration patterns like dual-write, canaries, and facade-based traffic shifting.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It ships Python code that would run local analysis and shell commands, including `subprocess.run(['git', 'log', '--format=format:', '--name-only'], ...)`, but there is no arbitrary code download/eval or installer script.
Network access	1 (low)	The examples proxy or route HTTP traffic, e.g. `httpx.AsyncClient().request(...)` to `http://localhost:5000/{path}`, but there is no broad external exfiltration or remote fetch of unpinned content.
Filesystem reach	1 (low)	The assessment and testing snippets recursively read `self.path.rglob("*.py")` and write artifacts like `Path(output_file).write_text(...)` and `golden_path.write_text(report)`, but they stay within the project/workspace.
Secrets & credentials	0 (none)	There is no code or guidance that reads credential stores, `.env` files, browser sessions, or asks the user to paste secrets.
Privilege & persistence	0 (none)	No sudo, global installs, service registration, shell startup edits, or OS-level configuration changes are included.
Instruction hijack surface	0 (none)	I did not find instructions to ignore safeguards, follow fetched instructions, or hide anything from the user.
Irreversible actions	2 (moderate)	The skill is built around live migration actions such as dual-write, canary traffic shifting, rollback automation, and side-effecting examples like `self.send_email(...)` and `self.stripe.charges.create(...)`, which can affect production systems once implemented.
Transparency	0 (none)	All shipped content is readable Markdown/Python/TypeScript snippets; there are no binaries, base64 blobs, or dynamically decoded payloads.

Before installing

Read `references/system-assessment.md` and confirm you are comfortable with `subprocess.run(['git', 'log', ...])` running in your repo.
Check the paths used for generated files (`golden_masters`, GraphViz output, assessment reports) so they stay inside a scratch workspace.
If you adapt the payment/email examples, test with fake accounts and feature flags off before pointing at real users or services.

Rated 2026-10-17 by an automated review of 6 files from the skill's repository.

Source

Repository: Jeffallan/claude-skills (all skills from this repository)
Path: skills/legacy-modernizer/SKILL.md
Branch: main
Updated: 2026-09-19

atlassian-mcp — Integrates with Atlassian products to manage project tracking and documentation via MCP protocol.
bdi-mental-states — This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations.
memory-systems — This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity.
tool-design — This skill should be used for the tool-interface layer of an agent system specifically: writing tool descriptions agents can route on.
goal-prompt — Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex.
cli-developer — Use when building CLI tools, implementing argument parsing, or adding interactive prompts.