planning-codebase-restructuring — Claude Code skill
planning-codebase-restructuring is a Claude Code skill that maps a codebase and prepares a restructuring plan without changing files. It produces an evidence-backed report for a later implementation pass.
no license 100 installs ★ 3 updated 2026-10-25
npx skills add b-mendoza/agent-skills --skill planning-codebase-restructuring -a claude-codeWhat planning-codebase-restructuring does
planning-codebase-restructuring maps the current architecture in read-only mode, examines domain language with DDD and Screaming Architecture, quarantines external references, and prepares a migration plan. Five subagents contribute to the workflow: an architecture cartographer, domain analyst, restructuring strategist, reference assessor, and plan reviewer.
The skill takes a repository path or URL, a target scope, business goals, and constraints. It can write the final report to ARTIFACT_PATH; a repository URL may also trigger a shallow temporary clone outside the target tree. Tests, builds, package installs, formatters, generators, file moves, refactors, and public-contract changes are outside its operation.
What it helps with
- draft a restructuring plan for a codebase
- map domain boundaries and business capabilities
- compare the current structure with DDD and Screaming Architecture
- assess an external architecture reference
- prepare a report for a later implementation run
Example prompts for the agent
- Create a restructuring plan for
CODEBASE_PATH_OR_REPOSITORY_URL, coveringTARGET_SCOPEandBUSINESS_GOALS_AND_PAIN_POINTS. - Map the current architecture through read-only inspection, check
KNOWN_DOMAIN_LANGUAGE, and save the result toARTIFACT_PATH. - Assess
REFERENCE_URLagainstCONSTRAINTSand produce a report usingSUCCESS_CRITERIA.
How to install planning-codebase-restructuring
1Skills CLI (Vercel)
npx skills add b-mendoza/agent-skills --skill planning-codebase-restructuring -a claude-code2Manually: put the files in place
~/.claude/skills/planning-codebase-restructuring/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/planning-codebase-restructuring/
1Skills CLI (Vercel)
npx skills add b-mendoza/agent-skills --skill planning-codebase-restructuring -a codex2Manually: put the files in place
.agents/skills/planning-codebase-restructuring/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add b-mendoza/agent-skills --skill planning-codebase-restructuring -a cursor2Manually: put the files in place
.cursor/skills/planning-codebase-restructuring/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install b-mendoza/agent-skills skills/planning-codebase-restructuring2Manually: put the files in place
.github/skills/planning-codebase-restructuring/SKILL.md1Skills CLI (Vercel)
npx skills add b-mendoza/agent-skills --skill planning-codebase-restructuring -a gemini-cli2Platform CLI
gemini skills install https://github.com/b-mendoza/agent-skills --path skills/planning-codebase-restructuringManually: put the files in place
.devin/skills/planning-codebase-restructuring/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add b-mendoza/agent-skills --skill planning-codebase-restructuring -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about planning-codebase-restructuring
How do I install planning-codebase-restructuring in Claude Code?
Run npx skills add b-mendoza/agent-skills --skill planning-codebase-restructuring -a claude-code, then use ~/.claude/skills/planning-codebase-restructuring/SKILL.md.
What does planning-codebase-restructuring do?
The skill reads a project, examines domain boundaries, reviews external references, and sends a candidate restructuring report to an independent reviewer. It does not modify the codebase.
What inputs does planning-codebase-restructuring need?
It needs CODEBASE_PATH_OR_REPOSITORY_URL, TARGET_SCOPE, and BUSINESS_GOALS_AND_PAIN_POINTS. Domain language, constraints, a reference URL, success criteria, and an artifact path are optional inputs.