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/d4rkninja/arcforge/migration-evolutionnpx skills add d4rkNinja/arcforge --skill migration-evolutiongit clone --depth 1 https://github.com/d4rkNinja/arcforgeWhat 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 | $0.00081 | $0.02276 |
| Opus 5 | $0.00041 | $0.01138 |
| Sonnet 5 | $0.00016 | $0.00455 |
| Haiku 4.5 | $0.00008 | $0.00228 |
Grade A, and why
migration-evolution 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 2d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Think Through Migrations & Evolution
Overview
Production guidance for changing running systems safely. Each reference paper captures the sequences that prevent outages: expand-and-contract instead of in-place renames, resumable backfills that do not overwrite newer writes, compatibility windows for old clients, CDC pipelines with reconciliation, and cutover plans with genuine rollback.
Core principle: A migration is a distributed system that runs while the old and new versions are both live. Every step must tolerate mixed versions, partial failure, and rollback — code rollback never undoes committed data.
Domain Law
NO MIGRATION WITHOUT:
1. the minimum required primary paper(s) for the change type selected from the context table;
2. current state, target state, and every intermediate state written
down before the first migration step;
3. "Existing-codebase checks" run against deployed versions, consumers,
and retained data — not just the latest code;
4. every applicable MUST mapped to a migration step, a verification gate,
or a documented exception.
When to Use
Use this skill when thinking through, reviewing, changing, or verifying:
- database schema migrations, online/zero-downtime migrations, lock behavior;
- additive vs destructive changes, column renames, type changes, nullability flips;
- data migrations and backfills: chunking, resuming, idempotency, rate control;
- API and event schema evolution with old consumers;
- backward/forward compatibility windows and deprecation sequencing;
- data synchronization between two systems during transition;
- change data capture pipelines and their failure/replay behavior;
- search index rebuilds and dual-index cutover;
- feature migration: moving behavior between services with traffic cutover;
- legacy integration: strangler patterns, adapters, retirement sequencing.
When Not to Use
- Transaction/outbox internals for avoiding dual writes: use
transactions-consistency(047). - CI/CD pipeline mechanics and deployment tooling: use
runtime-delivery(106, 107). - Whole-system replatforming or rewrite decisions: use
system-architecture-harness(references 18). - Contract design for new APIs: use
api-contracts.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 282 B
- examples/worked-example-email-column-rename.md 4.0 KB
- references/papers/029-schema-evolution.md 33 KB
- references/papers/030-database-migrations.md 40 KB
- references/papers/031-data-migrations-and-backfills.md 32 KB
- references/papers/070-api-event-schema-evolution.md 33 KB
- references/papers/071-backward-compatibility.md 31 KB
- references/papers/072-data-synchronization.md 30 KB
- references/papers/073-change-data-capture.md 40 KB
- references/papers/130-search-index-synchronization.md 33 KB
- references/papers/134-zero-downtime-changes.md 31 KB
- references/papers/135-feature-migration.md 31 KB
- references/papers/136-legacy-system-integration.md 30 KB
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.
- 2d ago First seen · 146 lines · 81 tokens per session scan A 6b1cecd04426
migration-evolution is a skill published in the GitHub repository d4rkNinja/arcforge (16 stars, last pushed 5d ago), licensed MIT. It adds 81 tokens to every session and 2,276 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
code-to-diagram
Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a…
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.
csv-to-sif
Export a project's FF&E product-library CSV as dealer-system SIF. Use to produce a .sif schedule; use sif-to-csv for the reverse direction.
modular-skills
Build composable skill modules with hub-and-spoke loading. Use when token budget is tight.
environmental-analysis
Research climate, sun, flood, seismic, soil, contamination, and topography for a site. Use for environmental site analysis or hazard questions tied to a location.