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 skills add celticht32/Couchbase-Skills-for-Claude.ai --skill couchbase-migration-executiongit clone --depth 1 https://github.com/celticht32/Couchbase-Skills-for-Claude.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/celticht32/couchbase-skills-for-claude.ai/couchbase-migration-execution)<a href="https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-migration-execution"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-migration-execution/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-migration-execution"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-migration-execution.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00209 | $0.02215 |
| Opus 5 | $0.00105 | $0.01107 |
| Sonnet 5 | $0.00042 | $0.00443 |
| Haiku 4.5 | $0.00021 | $0.00221 |
Grade A, and why
couchbase-migration-execution 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 11d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Couchbase migration execution
A skill for executing data migrations into Couchbase — the mechanics of moving data, keeping source and target in sync during transition, validating equivalence, and switching production traffic.
Distinct from the sibling skills:
couchbase-data-modeling— how to MODEL the data after migrating (document shape, boundaries, access patterns)couchbase-sizing— how to size the target clustercouchbase-app-integration— how to write app code that uses Couchbase (relevant during dual-write)couchbase-mcp— operating the cluster (creating the target, running queries during validation)couchbase-migration-execution(this skill) — the operational mechanics of moving data and switching over
If the conversation is "how do I get my data from X into Couchbase," this is the right skill.
When this skill applies
- "How do I migrate from MongoDB / Postgres / DynamoDB / MySQL to Couchbase?"
- "Should I do a big-bang migration or phased?"
- "What's dual-write?"
- "How do I keep the source and target in sync during migration?"
- "Can I use CDC for this?"
- "How do I validate the migration worked?"
- "How do I cut over production traffic?"
- "What if the migration goes wrong — can I roll back?"
- "Tooling for bulk loading into Couchbase?"
Pick the right reference
| Question | Read |
|---|---|
| "Big-bang vs phased vs strangler-fig vs dual-write — which approach?" | references/strategies.md |
| "What tools exist — cbimport, ETL frameworks, CDC tools?" | references/tooling.md |
| "Migrating from MongoDB specifically" | references/from-mongodb.md |
| "Migrating from PostgreSQL / MySQL / Oracle / SQL Server" | references/from-relational.md |
| "Migrating from DynamoDB / Cassandra / files / something else" | references/from-other-sources.md |
| "Dual-write code patterns, CDC setup, keeping source and target in sync" | references/dual-write-and-cdc.md |
| "Validating the migration + cutting over + rolling back if needed" | references/validation-and-cutover.md |
What ships with it
7 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.
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.
- 11d ago First seen · 137 lines · 209 tokens per session scan A 7f49c107af4d
couchbase-migration-execution is a skill published in the GitHub repository celticht32/Couchbase-Skills-for-Claude.ai (4 stars, last pushed 2mo ago), licensed MIT. It adds 209 tokens to every session and 2,215 once invoked, about $0.0010 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
database-migrator
Migrates databases between providers (Postgres, MySQL, Supabase, PlanetScale, MongoDB). Reads source schema, generates migration scripts, handles data type mapping, foreign keys, indexes, triggers, stored procedures. Validates migration with row counts and checksums. Generates migration-plan.md with step-by-step…
database-schema-designer
Design optimized database schemas for SQL and NoSQL databases including tables, relationships, indexes, and constraints. Creates ERD diagrams, migration scripts, and data modeling best practices. Use when users need database design, schema optimization, or data architecture planning.
using-document-databases
Document database implementation for flexible schema applications. Use when building content management, user profiles, catalogs, or event logging. Covers MongoDB (primary), DynamoDB, Firestore, schema design patterns, indexing strategies, and aggregation pipelines.
mongodb
A guide for managing MongoDB, a database that stores records in flexible document collections. It covers local, remote, and replica-set connections, database and collection administration, data operations, and indexes.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
316-frameworks-spring-mongodb-migrations-mongock
Use when you need to add or review Mongock MongoDB data migrations in a Spring Boot application — including Maven coordinates, Spring Data MongoDB drivers, migration scan packages, @ChangeUnit classes, lock/transaction settings, and optional policy-approved MongoDB integration verification. This should trigger for…