agentleFS
RidhuanDEVRidhuanDEV/claude-skills/shadow-modernize/SKILL.md

shadow-modernize

Skill1 starsChanged yesterdayMITView on GitHub

Technical Due Diligence & Legacy Modernization. Use when auditing inherited/legacy systems, performing business-rule archaeology, scoring multi-dimensional risk vectors, or comparing Strangler Fig Refactor vs Full Rewrite TCO including coexistence costs.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill whenever the Monarch invokes /shadow-modernize, audits an inherited/legacy codebase or vendor system, performs M&A/handover …

    line 8
  2. Very specific:

    Before proposing migration cuts, cross-reference database triggers/constraints/stored procedures, API validators, batch cron jobs, and …

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/shadow-modernize — Technical Due Diligence & Migration Intelligence

Use this skill whenever the Monarch invokes /shadow-modernize, audits an inherited/legacy codebase or vendor system, performs M&A/handover technical due diligence, or evaluates Strangler Fig Refactor vs Rewrite modernization economics.

Integrates with shadow-monarch/reference/CONSULTING-INTELLIGENCE-CORE.md and deep methodologies:

  • methodologies/TECHNICAL-FORENSICS-AND-MIGRATION-ECONOMICS.md — 8-Area Technical Due Diligence, Multi-Dimensional Risk Vectors with Evidence Confidence, Business-Rule Archaeology, and Migration Economics (coexistence & transition cost).
  • playbooks/DUE-DILIGENCE-AND-CUTOVER-TEMPLATES.md — System Archaeology Report, Technical Risk Register, Migration Dependency Map, Modernization Business Case, Cutover Plan, and Rollback Playbook.

1. Execution Contract (Never Produce Opaque Single Tech-Debt Scores)

  1. Read-Only Forensics by Default: Inspect repositories, schemas, dependency lockfiles, CI/CD, and operational telemetry read-only, recording SHA-256 evidence digests and explicit access limitations (e.g., no prod telemetry or DB access).
  2. Multi-Dimensional Risk Vector (Not One Black-Box Score):
    • Score 8 dimensions separately (code_dependencies, architecture_coupling, data_integrity, operations_slo, security_supply_chain, business_criticality) with configurable weights and explicit evidence_confidence (HIGH/MEDIUM/LOW).
    • Critical Rule: Absence of automated tests does NOT automatically mandate a FULL_REWRITE. A stable core system carrying complex undocumented business rules and high downtime cost is frequently safer to preserve via Characterization Tests + Strangler Fig / Branch by Abstraction.
  3. Business-Rule Archaeology:
    • Before proposing migration cuts, cross-reference database triggers/constraints/stored procedures, API validators, batch cron jobs, and historical incident workarounds to surface hidden domain invariants.
  4. Migration Economics (Refactor vs Rewrite TCO):
    • Model build_transition_cost + dual_run_coexistence_cost + data_reconciliation_cost + risk_adjusted_delay_cost across 3–5 years for STRANGLER_FIG_REFACTOR, PHASED_MODULARIZATION, ENCAPSULATE_RETAIN, and FULL_REWRITE.

2. Deterministic Forensics & Economics Engine

python "shadow-modernize/scripts/modernize_forensics_engine.py" --self-test
python "shadow-modernize/scripts/modernize_forensics_engine.py" --scan-repo path/to/legacy_repo
python "shadow-modernize/scripts/modernize_forensics_engine.py" --evaluate-options path/to/system_profile.json

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.