Agent skill

Code Migrator

by FerroxLabs in FerroxLabs/wayland

Code migration specialist covering planning frameworks, strangler fig pattern, compatibility layers, feature flags, database migrations, API versioning, rollback plans, and testing migration…

Apache-2.0Auto-check passedDatabases

Install Code Migrator

skills CLI
$ npx skills add FerroxLabs/wayland --skill code-migrator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install FerroxLabs/wayland code-migrator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/FerroxLabs/wayland.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/process/resources/skills-library/bodies/skills/software-engineering/code-migrator .claude/skills/code-migrator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
code-migrator
GitHub stars
608
Token cost
~3.7k tokens
SKILL.md length
1,067 words
Files
1
Skills in repo
1,194
Repo updated
First seen
Licence
Apache-2.0

At a glance

Code migration specialist covering planning frameworks, strangler fig pattern, compatibility layers, feature flags, database migrations, API versioning, rollback plans, and testing migration…

  • Works in 3 steps: Assessment → Strategy Selection → Execution Plan
  • The user asks about code migrator
  • SKILL.md covers Migration Planning Framework, Strangler Fig Pattern, Branch by Abstraction and Feature Flags for Migration, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Code Migrator is an agent skill from FerroxLabs/wayland. Code migration specialist covering planning frameworks, strangler fig pattern, compatibility layers, feature flags, database migrations, API versioning, rollback plans, and testing migration completeness. Use when the user asks about code migrator, code migrator best practices, or needs guidance on code migrator implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Databases, covering Database migrations and Code migrations. The repository describes itself as: Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves. The licence is Apache-2.0.

When your agent uses it

  • The user asks about code migrator
  • Code migrator best practices
  • Needs guidance on code migrator implementation
  • The user needs a different specialized skill

Example prompts

  • “/code-migrator”

Requirements

  • Python 3
  • Node.js

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Assessment
  2. Strategy Selection
  3. Execution Plan

What it can do on your machine

Read from SKILL.md and the folder at commit 4c030c7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown, python, sql, javascript and typescript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Code Migrator loads about 3.7k tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 1,067 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~114
When it runs · the whole SKILL.md, loaded when a task matches
~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from FerroxLabs/wayland at commit 4c030c7, republished under its Apache-2.0 licence (© FerroxLabs). 1,067 words, ~3,717 tokens.

Download SKILL.mdSave it as .claude/skills/code-migrator/SKILL.md (or your agent's skills folder).
name
code-migrator
description
Code migration specialist covering planning frameworks, strangler fig pattern, compatibility layers, feature flags, database migrations, API versioning, rollback plans, and testing migration completeness. Use when the user asks about code migrator, code migrator best practices, or needs guidance on code migrator implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.
license
Apache-2.0
metadata.author
foundry-skills
metadata.version
1.0.0
metadata.tags
best-practices clean-code automation
metadata.category
software-engineering
metadata.subcategory
developer-tools
metadata.disclaimer
none
metadata.difficulty
intermediate

Code Migrator

You are an expert code migration specialist. Plan and execute migrations that are incremental, reversible, and verifiable. Never attempt big-bang migrations. Every migration step must leave the system in a working state.

Migration Planning Framework

Phase 1: Assessment
  1. Inventory: What needs to migrate? (files, modules, APIs, data, infrastructure)
  2. Dependencies: What depends on the thing being migrated?
  3. Risk analysis: What is the blast radius if migration fails?
  4. Effort estimation: How many person-weeks per component?
  5. Success criteria: How do you know migration is complete?
Phase 2: Strategy Selection
StrategyBest forRiskDuration
Strangler FigReplacing system incrementallyLowLong
Branch by AbstractionSwapping implementationsLowMedium
Big BangSmall, isolated componentsHighShort
Parallel RunCritical systems needing validationLowLong
Blue-GreenInfrastructure migrationsMediumShort
Phase 3: Execution Plan

Create a migration checklist with ordered steps:

markdown
## Migration: React Class Components -> Hooks

### Pre-migration
- [ ] Audit: List all class components (found: 47)
- [ ] Categorize by complexity (simple: 30, medium: 12, complex: 5)
- [ ] Write integration tests for components without coverage
- [ ] Set up linting rule to warn on new class components

### Migration waves
- [ ] Wave 1: Simple components (no lifecycle, no state)    [Week 1-2]
- [ ] Wave 2: Stateful components (useState conversion)     [Week 3-4]
- [ ] Wave 3: Lifecycle components (useEffect conversion)   [Week 5-6]
- [ ] Wave 4: Complex components (HOCs, render props)       [Week 7-8]
- [ ] Wave 5: Shared/library components                     [Week 9-10]

### Post-migration
- [ ] Remove class component utilities/base classes
- [ ] Update coding standards documentation
- [ ] Enable lint rule to error on class components
- [ ] Remove React.Component from allowed types

Strangler Fig Pattern

The most reliable migration pattern. Replace old functionality piece by piece while the old system continues to work.

How It Works
Phase 1: Route traffic through a facade
    Client -> [Facade] -> [Old System]

Phase 2: Implement new component, route some traffic to it
    Client -> [Facade] -> [New Component A]
                       -> [Old System (rest)]

Phase 3: Continue until old system has no traffic
    Client -> [Facade] -> [New Component A]
                       -> [New Component B]
                       -> [New Component C]
                       -> [Old System (empty)]

Phase 4: Remove old system
    Client -> [Facade] -> [New Component A]
                       -> [New Component B]
                       -> [New Component C]
Implementation Steps
  1. Create a routing layer (proxy, facade, adapter) in front of the old system.
  2. Identify the first piece to migrate (choose the simplest, most isolated piece).
  3. Implement the new version of that piece.
  4. Route traffic for that piece to the new implementation.
  5. Verify correctness (compare old and new outputs).
  6. Remove the old implementation of that piece.
  7. Repeat for the next piece.
Example: Migrating Express Routes to Fastify
javascript
// Facade: proxy routes to old or new handler
app.all('/api/*', (req, res) => {
  const migratedRoutes = ['/api/users', '/api/users/:id'];

  if (migratedRoutes.some(r => req.path.match(routeToRegex(r)))) {
    return fastifyApp.inject({ method: req.method, url: req.url, payload: req.body })
      .then(response => res.status(response.statusCode).send(response.body));
  }

  return oldExpressRouter.handle(req, res);
});

Branch by Abstraction

Use when swapping an internal implementation (e.g., replacing an ORM, changing a data store).

Steps
  1. Create an abstraction (interface) over the current implementation.
  2. Refactor all callers to use the abstraction instead of the concrete implementation.
  3. Build the new implementation behind the same abstraction.
  4. Switch the abstraction to use the new implementation (via config, feature flag, or DI).
  5. Remove the old implementation.
python
# Step 1: Create abstraction
class UserRepository(Protocol):
    def get_user(self, user_id: str) -> User: ...
    def save_user(self, user: User) -> None: ...

# Step 2: Wrap old implementation
class MySQLUserRepository:
    def get_user(self, user_id: str) -> User:
        # existing MySQL code
        ...

# Step 3: Build new implementation
class PostgresUserRepository:
    def get_user(self, user_id: str) -> User:
        # new PostgreSQL code
        ...

# Step 4: Switch via configuration
def create_user_repository(config) -> UserRepository:
    if config.use_postgres:
        return PostgresUserRepository(config.pg_url)
    return MySQLUserRepository(config.mysql_url)

Feature Flags for Migration

Use feature flags to control migration rollout and enable instant rollback.

Flag Types for Migration
Flag TypeUse CaseLifetime
Release flagGate new implementationWeeks
Experiment flagA/B test old vs newDays-weeks
Ops flagKill switch for rollbackPermanent until removed
Permission flagMigrate specific users/tenants firstWeeks
Gradual Rollout Strategy
Day 1:   Enable for internal users only          (1% traffic)
Day 3:   Enable for beta users                    (5% traffic)
Day 7:   Enable for 10% of all users             (10% traffic)
Day 10:  Enable for 50%                           (50% traffic)
Day 14:  Enable for 100%                          (100% traffic)
Day 21:  Remove flag and old code                 (cleanup)
Flag Implementation
typescript
async function getUser(userId: string): Promise<User> {
  if (await featureFlags.isEnabled('use-new-user-service', { userId })) {
    return newUserService.getUser(userId);
  }
  return legacyUserService.getUser(userId);
}

Database Migration Strategies

Schema Migrations
Expand-Contract Pattern (Zero Downtime)

Expand phase (backward-compatible):

  1. Add new column (nullable or with default).
  2. Deploy code that writes to both old and new columns.
  3. Backfill new column from old column data.
  4. Deploy code that reads from new column.

Contract phase (cleanup): 5. Deploy code that stops writing to old column. 6. Drop old column.

sql
-- Step 1: Expand - add new column
ALTER TABLE users ADD COLUMN full_name VARCHAR(255);

-- Step 3: Backfill
UPDATE users SET full_name = CONCAT(first_name, ' ', last_name) WHERE full_name IS NULL;

-- Step 6: Contract - remove old columns (after code migration complete)
ALTER TABLE users DROP COLUMN first_name;
ALTER TABLE users DROP COLUMN last_name;
Data Migration Tools
EcosystemToolNotes
Node.jsKnex, TypeORM, Prisma MigrateJS-based migration files
PythonAlembic, Django migrationsAuto-generated from models
JavaFlyway, LiquibaseSQL or XML-based
Gogolang-migrate, gooseSQL-based
RubyActiveRecord MigrationsRuby DSL
Migration Safety Rules
  1. Never delete a column in the same deploy that stops using it. Wait at least one deploy cycle.
  2. Never rename a column directly. Use expand-contract (add new, copy, drop old).
  3. Always make migrations reversible. Include a down/rollback migration.
  4. Never run data backfills in the migration transaction. Run them separately, in batches.
  5. Test migrations against production-sized data. A migration that takes 1 second on test data may take 4 hours on production data.
Data Store Migrations (e.g., MySQL to PostgreSQL)
  1. Set up dual-write: write to both old and new stores.
  2. Backfill: copy historical data from old to new store.
  3. Verify: compare data between stores (checksums, sampling).
  4. Switch reads to new store (behind feature flag).
  5. Verify reads return correct data.
  6. Stop writes to old store.
  7. Decommission old store.

API Versioning During Migration

Versioning Strategies
StrategyExampleProsCons
URL path/v1/users, /v2/usersSimple, explicitURL clutter
HeaderAccept: application/vnd.api+json;version=2Clean URLsEasy to skip
Query param/users?version=2SimplePollutes query string
Show full SKILL.md (424 more words)Show less
API Migration Steps
  1. Deploy v2 alongside v1 (both work).
  2. Update documentation to recommend v2.
  3. Notify consumers with deprecation timeline.
  4. Add deprecation headers to v1 responses: Deprecation: true, Sunset: 2024-06-01.
  5. Monitor v1 traffic. Contact remaining consumers.
  6. After sunset date, return 410 Gone for v1.
  7. Remove v1 code.
Backward-Compatible API Changes (Safe)
  • Adding a new endpoint
  • Adding a new optional field to request
  • Adding a new field to response
  • Adding a new query parameter
Breaking API Changes (Require New Version)
  • Removing or renaming a field
  • Changing a field's type
  • Changing validation rules to be more restrictive
  • Changing the response structure
  • Changing authentication requirements

Rollback Plans

Every migration step must have a documented rollback procedure.

Rollback Template
markdown
## Rollback Plan: [Migration Step Name]

### Trigger conditions
- Error rate exceeds 1% on affected endpoints
- P95 latency exceeds 500ms (baseline: 200ms)
- Data inconsistency detected between old and new systems

### Rollback steps
1. Disable feature flag `use-new-service` (immediate, < 1 minute)
2. Verify traffic routes to old system (check dashboards)
3. If database migration was applied:
   a. Run rollback migration: `migrate down 1`
   b. Verify schema matches pre-migration state
4. Notify team in #incidents channel

### Rollback verification
- [ ] Old system handles traffic correctly
- [ ] Error rate returns to baseline
- [ ] No data was lost or corrupted

### Post-rollback analysis
- What caused the rollback?
- What needs to change before retrying?

Testing Migration Completeness

Verification Strategies
  1. Shadow testing: Run both old and new systems, compare outputs for every request.
python
async def get_user_with_verification(user_id):
    old_result = await old_service.get_user(user_id)
    new_result = await new_service.get_user(user_id)

    if old_result != new_result:
        logger.error(f"Mismatch for user {user_id}",
                     old=old_result, new=new_result)
        metrics.increment("migration.mismatch")

    return old_result  # still serve from old system
  1. Data checksums: Compare aggregated data between systems.
sql
-- Row count comparison
SELECT COUNT(*) FROM old_db.users;
SELECT COUNT(*) FROM new_db.users;

-- Checksum comparison (sample)
SELECT MD5(GROUP_CONCAT(id, email, created_at ORDER BY id))
FROM old_db.users WHERE id BETWEEN 1 AND 10000;
  1. Integration test suite: Run the same test suite against both implementations.

  2. Canary analysis: Compare error rates and latency between old and new systems during gradual rollout.

Migration Completeness Checklist
  • All functional tests pass against new implementation
  • Performance benchmarks meet or exceed old implementation
  • Data integrity verified (row counts, checksums, sampling)
  • Monitoring and alerting configured for new system
  • Rollback procedure tested
  • Documentation updated
  • Old code and infrastructure removal scheduled
  • Feature flags cleaned up

Communication Template

Migration Announcement
markdown
## Migration: [Old Thing] -> [New Thing]

**Timeline**: [Start Date] to [End Date]
**Impact**: [Who is affected and how]
**Action required**: [What consumers need to do]

### Why
[1-2 sentences on motivation]

### What changes
[Specific changes consumers will see]

### Migration steps for consumers
1. [Step 1]
2. [Step 2]

### Support
- Questions: #migration-channel
- Issues: [link to issue tracker]
- Docs: [link to migration guide]

When to Use

Use this skill when:

  • Designing or implementing code migrator solutions
  • Reviewing or improving existing code migrator approaches
  • Making architectural or implementation decisions about code migrator
  • Learning code migrator patterns and best practices
  • Troubleshooting code migrator-related issues

Do NOT use this skill when:

  • The question is about a fundamentally different technology domain
  • A more specific sibling skill covers the exact topic needed
  • The user needs a complete hands-on tutorial rather than expert guidance

Output Format

markdown
# Code Migrator Analysis

## Context Assessment
[Situation summary and constraints]

## Recommended Approach
[Primary recommendation with rationale]

## Implementation Steps
1. [Step with specific details]
2. [Step with specific details]
3. [Step with specific details]

## Trade-offs and Considerations
- [Key trade-off 1]
- [Key trade-off 2]

## Next Steps
- [Immediate action item]
- [Follow-up action item]

Example

Input: "Help me implement code migrator for a medium-scale production application"

Output: A structured analysis covering current state assessment, recommended code migrator approach with specific patterns, implementation roadmap with milestones, and risk mitigation strategies tailored to the application scale and constraints.

Edge Cases

  • Legacy system integration: When code migrator must coexist with legacy approaches, provide a gradual migration path rather than a complete rewrite
  • Scale mismatch: When the solution complexity exceeds the project scale, recommend a simpler approach and note when to revisit
  • Team skill gaps: When the team lacks experience with the recommended approach, include learning resources and simpler alternatives
  • Conflicting requirements: When constraints conflict (e.g., performance vs. maintainability), explicitly state the trade-off and recommend based on stated priorities

© FerroxLabs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in src/process/resources/skills-library/bodies/skills/software-engineering/code-migrator of FerroxLabs/wayland.

Open the folder on GitHubat commit 4c030c7

Compare with similar skills

Code Migrator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Code Migrator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Migrator this skillFerroxLabs/wayland608—~3.7kAutomated safety check: PassApache-2.0
Data Migrationrevfactory/harness-1001.3k—~1.8kAutomated safety check: PassApache-2.0
Free Willsyahiidkamil/Software-Engineer-AI-Agent-Atlas397—~3.4kAutomated safety check: PassNone
Reversible MigrationJuliusBrussee/caveman110k1 repos~196Automated safety check: PassApache-2.0
Evolving The Data ModelTriliumNext/Trilium38k—~2.1kAutomated safety check: PassAGPL-3.0
Openwrt Package UpdateNethServer/nethsecurity191—~841Automated safety check: PassCustom licence

Similar skills

  • Data Migration

    revfactory/harness-100

    Full migration pipeline where an agent team collaborates to perform source analysis, schema mapping, transformation script generation, validation query design, and rollback planning.

    1.3k GitHub stars~1.8k tokensUpdated 6 mo ago
    DatabasesAuto-check passed
  • Free Will

    syahiidkamil/Software-Engineer-AI-Agent-Atlas

    Deliberate-choice procedure for a medium-to-high-stakes engineering fork — when the first plausible solution (the instinct, the default next-token pull) would be costly to get wrong.

    397 GitHub stars~3.4k tokensUpdated 3 mo ago
    DatabasesAuto-check passed
  • Reversible Migration

    JuliusBrussee/caveman

    Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and…

    110k GitHub starsUsed in 1 repo~196 tokens
    DevelopmentAuto-check passed
  • Evolving The Data Model

    TriliumNext/Trilium

    A skill your agent uses when adding a DB migration or a new column/field to a Becca entity in Trilium ("add a migration", "new column on notes/attributes", "ALTER TABLE", "add a field to…

    38k GitHub stars~2.1k tokensUpdated today
    DatabasesAuto-check passed
  • Openwrt Package Update

    NethServer/nethsecurity

    A skill your agent uses when updating any forked OpenWrt package in a NethSecurity workspace from the upstream openwrt/packages feed.

    191 GitHub stars~841 tokensUpdated yesterday
    DatabasesAuto-check passed
  • Saleor Port Changes

    saleor/saleor

    Forward-ports or backports a single PR or branch onto the currently checked-out Saleor branch, handling GraphQL version markers and migration numbering along the way.

    23k GitHub stars~969 tokensUpdated yesterday
    DevelopmentAuto-check passed

More from FerroxLabs/wayland

All 1,194 skills in this repo
  • Star Office Helper

    FerroxLabs/wayland

    Install, start, connect, and troubleshoot visualization companion projects for Aion/OpenClaw, with Star-Office-UI as the default recommendation.

    608 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check: notes
  • Openclaw Setup

    FerroxLabs/wayland

    OpenClaw usage expert: Helps you install, deploy, configure, and use OpenClaw personal AI assistant.

    608 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Tvcontrol Setup

    FerroxLabs/wayland

    Set up TVControl end to end: install the connector, start TradingView Desktop with its control port open, load a watchlist export, add the indicators they use, and leave a working chart.

    608 GitHub stars~5.7k tokensUpdated yesterday
    Auto-check passed
  • Ab Testing Specialist

    FerroxLabs/wayland

    End-to-end guide for designing, running, and analyzing A/B tests including experiment design, statistical significance, sample size calculation, common pitfalls, and advanced testing patterns.

    608 GitHub stars~3.7k tokensUpdated yesterday
    Auto-check passed
  • Academic Writer

    FerroxLabs/wayland

    Complete academic writing guide covering thesis and dissertation structure, journal article format using IMRaD, literature review methodology, citation management, the peer review process, and…

    608 GitHub stars~4.5k tokensUpdated yesterday
    Auto-check passed
  • Accessibility Auditor

    FerroxLabs/wayland

    Web accessibility expertise covering WCAG 2.2 conformance, audit methodology, ARIA patterns, keyboard navigation, screen reader testing, focus management, form accessibility, and automated vs manual…

    608 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed

Questions about Code Migrator

What does Code Migrator do?

Code migration specialist covering planning frameworks, strangler fig pattern, compatibility layers, feature flags, database migrations, API versioning, rollback plans, and testing migration…. Code Migrator is an agent skill from FerroxLabs/wayland. Code migration specialist covering planning frameworks, strangler fig pattern, compatibility layers, feature flags, database migrations, API versioning, rollback plans, and testing migration completeness.

When should I use Code Migrator?

Code Migrator fits situations like: the user asks about code migrator; code migrator best practices; needs guidance on code migrator implementation; the user needs a different specialized skill.

How do I install Code Migrator in Claude Code?

Run `npx skills add FerroxLabs/wayland --skill code-migrator -a claude-code`. Or copy the skill folder (src/process/resources/skills-library/bodies/skills/software-engineering/code-migrator in FerroxLabs/wayland) into .claude/skills/code-migrator in your project. Claude Code loads it when a task matches its description.

How do I install Code Migrator in Codex?

Run `npx skills add FerroxLabs/wayland --skill code-migrator -a codex`. Or copy the skill folder (src/process/resources/skills-library/bodies/skills/software-engineering/code-migrator in FerroxLabs/wayland) into .agents/skills/code-migrator in your project. Codex loads it when a task matches its description.

Can I use Code Migrator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add FerroxLabs/wayland --skill code-migrator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-migrator, .gemini/skills/code-migrator, .github/skills/code-migrator and .opencode/skills/code-migrator in your project.

What does Code Migrator need to run?

SKILL.md names no scripts, command-line tools or credentials: Code Migrator is instructions for the agent only. Our summary lists: Python 3; Node.js.

Does Code Migrator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Code Migrator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Code Migrator use?

Code Migrator is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Migrator use?

About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Code Migrator?

Skills that share tags, products or a category with Code Migrator: Data Migration (revfactory/harness-100, 1.3k stars), Free Will (syahiidkamil/Software-Engineer-AI-Agent-Atlas, 397 stars), Reversible Migration (JuliusBrussee/caveman, 110k stars) and Evolving The Data Model (TriliumNext/Trilium, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Migrator?

FerroxLabs (a GitHub user) maintains it in FerroxLabs/wayland, which has 608 GitHub stars. The repository holds 1,194 skills in this directory. The repository was last updated on October 6, 2026.

Source: FerroxLabs/wayland on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.