sdlc-modernize

sdlc-modernize is a command for coding agents from saitarrun/Devforge-ai. It costs 24 tokens per session (458 once invoked), scanned A, original, Apache-2.0.

A command for gradually replacing or separating older software while keeping the existing system running. It includes techniques for recording current behavior, placing a clean interface around old code, moving traffic in stages, and changing databases safely.

In plain words
What is it for?
Use it to modernize old code, split a monolith into smaller services, replace stored procedures, or move database data without planned downtime. A monolith is one large application containing many parts that could later be separated.
Why use it?
It reduces the risk of breaking a legacy system during modernization. The existing behavior can be captured and new parts can be introduced incrementally.

Command

Part of the devforge-ai plugin — 28 skills, 17 commands, 13 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/saitarrun/devforge-ai/sdlc-modernize
Clone the repo
git clone --depth 1 https://github.com/saitarrun/Devforge-ai

Or install devforge-ai, the plugin that ships this one along with the rest of its 28 skills, 17 commands, 13 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for sdlc-modernize

README.md
[![agentmods](https://agentmods.dev/badge/commands/saitarrun/devforge-ai/sdlc-modernize.svg)](https://agentmods.dev/commands/saitarrun/devforge-ai/sdlc-modernize)
Your own site
<a href="https://agentmods.dev/commands/saitarrun/devforge-ai/sdlc-modernize"><img src="https://agentmods.dev/badge/commands/saitarrun/devforge-ai/sdlc-modernize.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.00458
Opus 5 $0.00012 $0.00229
Sonnet 5 $0.00005 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 4d ago against content hash 67665de0d679, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-modernize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/sdlc-modernize.md · 46 lines

What it actually says

Industrial Legacy Modernization & Migration Command

This command enables safe extraction, characterization testing, and modern decoupling of legacy monoliths, stored procedures, and outdated frameworks without downtime or breaking changes.

Usage

/sdlc-modernize "legacy_policy_engine.c" --snapshot-tests  # Create Golden Master characterization tests
/sdlc-modernize src/monolith/claims/ --pattern strangler   # Generate Strangler Fig proxy & microservice slice
/sdlc-modernize "StoredProc_CalculatePremium" --pattern acl # Extract SQL procedure into typed domain service

Process

  1. Golden Master Characterization:
    • Synthesizes automated snapshot tests recording inputs and outputs across all legacy edge cases.
  2. Anti-Corruption Layer (ACL) Generation:
    • Wraps legacy types, raw SQL, and global state behind clean, typed interface seams.
  3. Strangler Fig Routing Setup:
    • Creates dual-write and shadow-traffic proxy configs for incremental traffic migration.
  4. Expand & Contract Database Evolution:
    • Generates zero-downtime migration scripts and backfill background workers.

Output Format

### 🏛️ Legacy Modernization Plan: [Target Module]

**Modernization Strategy**: Strangler Fig with Anti-Corruption Layer (ACL)

#### 🧪 Golden Master Characterization Suite
- Generated `tests/characterization/legacy_policy.spec.ts` (100% snapshot parity on 500 test scenarios)

#### 🔌 Anti-Corruption Layer (ACL)
- Created `src/domain/policy/policy.adapter.ts` (Translates legacy database records into domain models)

#### 🔄 Dual-Write & Shadow Traffic Configuration
- Proxy Route: `POST /api/v2/policies` (Shadow compares Legacy vs New Engine)
- Zero-Downtime Migration: Expand-Contract schema migration written to `migrations/20260813_policy_v2.sql`
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 46 lines · 24 tokens per session scan A 67665de0d679

Subscribe to this mod's changes

sdlc-modernize is a command published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 21d ago), licensed Apache-2.0. It adds 24 tokens to every session and 458 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.