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.
npx agentmods add skills/saitarrun/devforge-ai/legacy-modernizationnpx skills add saitarrun/Devforge-ai --skill legacy-modernizationgit clone --depth 1 https://github.com/saitarrun/Devforge-aiWrote 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.
[](https://agentmods.dev/skills/saitarrun/devforge-ai/legacy-modernization)<a href="https://agentmods.dev/skills/saitarrun/devforge-ai/legacy-modernization"><img src="https://agentmods.dev/badge/skills/saitarrun/devforge-ai/legacy-modernization.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.00723 |
| Opus 5 | $0.00016 | $0.00362 |
| Sonnet 5 | $0.00007 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
legacy-modernization 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Industrial Legacy Code Modernization & Migration Skill
This skill defines the strategy for safely refactoring, decoupling, and migrating mission-critical legacy systems (e.g., COBOL backends, 15-year-old monoliths, stored-procedure-heavy databases, PHP/Java EE stacks, and undocumented C++/C# engines) without production outages.
1. The Strangler Fig Modernization Pattern
Never attempt a "Big Bang" rewrite of an industrial legacy application. Always use the Strangler Fig Pattern:
[Phase 1: Ingress Interception & Routing Proxy]
↳ Direct traffic through an API gateway / reverse proxy (Envoy / Cloudflare / Nginx).
↓
[Phase 2: Shadow Traffic & Dark Launching]
↳ Duplicate live production requests to both the Legacy System and the Modern Microservice.
↳ Compare responses; assert 100% data equality (diff assertions) without returning modern output to clients yet.
↓
[Phase 3: Incremental Traffic Shifting]
↳ Route 1% → 10% → 50% → 100% of read traffic to the new service.
↓
[Phase 4: Legacy Strangling & Decommissioning]
↳ Decommission the legacy code path once all mutations and reads are fully migrated.
2. Reverse-Engineering Undocumented Legacy Code
When dealing with 100k+ lines of undocumented legacy spaghetti code:
- Golden Master Characterization Testing:
- Before editing a single line, record input/output snapshots of the legacy system across hundreds of real-world scenarios.
- Lock down behavior with automated characterization test suites.
- Extract Seams & Anti-Corruption Layers (ACL):
- Introduce an Anti-Corruption Layer (ACL) between legacy data structures and modern domain models to prevent legacy naming/type pollution.
- Database Stored-Procedure Extraction:
- Extract raw SQL triggers, cursors, and stored procedures into explicit, version-controlled domain services.
3. Zero-Downtime Database Migration (Expand & Contract)
When modifying legacy schemas touching millions of production records:
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.
- 5d ago First seen · 77 lines · 33 tokens per session scan A 14d2eab245ef
legacy-modernization is a skill published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 22d ago), licensed Apache-2.0. It adds 33 tokens to every session and 723 once invoked, about $0.0002 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.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
init
Set up docflow in a repo with no docs yet: scaffold the docs tree, write docflow.json, add agent guidance. Use when asked to "set up docflow", "initialize docs", "scaffold docs", or "make this repo use docflow".
status
Set a status message on your DevGlobe profile.
moss-comments
Comment annotation and sidecar rules for Moss notes. Use when adding, replying to, resolving, preserving, or editing comments and comments.json.
adr-workflow
Scaffold, accept, index, and link Architectural Decision Records (ADRs). Use when the user says "write an ADR", "record this decision", "resolve [deferred item] with an ADR", "supersede ADR-NNNN", or otherwise wants to capture a hard-to-reverse decision in docs/decisions/. Also use when a refinement-todo entry needs…