couchbase-magma

couchbase-magma is a skill for Claude Code, Codex from celticht32/Couchbase-Skills-for-Claude.ai. It costs 158 tokens per session (1,501 once invoked), scanned A, original, MIT.

A guide to Magma, Couchbase’s storage engine for keeping database data on disk, especially on nodes holding large datasets. It explains how Magma compares with the older Couchstore engine.

In plain words
What is it for?
Use it to compare Magma with Couchstore, understand vBuckets and compaction, estimate memory needs, and configure storage when creating or upgrading a bucket.
Why use it?
It helps choose the storage engine and settings that fit the dataset size, read and write workload, memory, and disk layout.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to compare Magma with Couchstore, understand vBuckets and compaction, estimate memory needs, and configure storage when creating or upgrading a bucket.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/celticht32/couchbase-skills-for-claude.ai/couchbase-magma
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.

Any agent
npx skills add celticht32/Couchbase-Skills-for-Claude.ai --skill couchbase-magma
Clone the repo
git clone --depth 1 https://github.com/celticht32/Couchbase-Skills-for-Claude.ai

Made for: Claude Code, Codex.

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 couchbase-magma

README.md
[![agentmods](https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-magma/github.svg)](https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-magma)
Your own site
<a href="https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-magma"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-magma/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.

agentmods 80×15 button for couchbase-magma

Your own site · 80×15
<a href="https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-magma"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-magma.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 158 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,501 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00158 $0.01501
Opus 5 $0.00079 $0.00750
Sonnet 5 $0.00032 $0.00300
Haiku 4.5 $0.00016 $0.00150

Measured 12d ago against content hash 880ccb115383, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

couchbase-magma 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 12d 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.

skills/couchbase/couchbase-magma/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Couchbase Magma Storage Engine

A skill for understanding and tuning the Magma storage engine — Couchbase's LSM-tree-based storage backend optimized for large datasets per node.

When this skill applies

  • "Should I use Magma or couchstore for my bucket?"
  • "What changed with Magma being the default in 8.0?"
  • "What does 128 vBuckets mean vs 1024?"
  • "How does Magma handle compaction differently?"
  • "How much memory does Magma need?"
  • "My write performance is different after upgrading to 8.0"
  • "How do I set the storage engine when creating a bucket?"

Magma vs couchstore at a glance

Couchstore (classic) Magma
Architecture B-tree per vBucket LSM-tree per vBucket
Default vBuckets 1024 128 (8.0 default)
RAM per node minimum 100 MB per bucket (min); memory-to-data ratio 10% 100 MB (128 vBucket) / 1 GiB (1024 vBucket); memory-to-data ratio 1%
Optimized for Smaller datasets, high read ratio Large datasets (>100M docs/node), high write rate
Write performance Good at low-moderate write rates Better at sustained high write rates (LSM absorbs bursts)
Read performance Excellent (direct B-tree lookup) Good (may require multi-level lookup on cold data)
Compaction Explicit compaction cycle Continuous background compaction (no manual trigger needed)
Disk space efficiency Good after compaction Good continuously (LSM merges in background)
Available CE and EE EE only

When to use Magma

Use Magma when:

  • Dataset exceeds ~100M documents per node
  • Write rate is high and sustained (> 50K writes/sec per node)
  • Memory is constrained (Magma's minimum per-bucket RAM is lower)
  • You're using fullEviction (Magma pairs well with fullEviction's design)

Stick with couchstore when:

  • Dataset is small-to-medium (< 50M documents per node)
  • Read performance is critical and the working set fits in RAM
  • You're on Community Edition
  • You need to stay on 1024 vBuckets for an existing operational reason

Read the full file on GitHub · 114 lines

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. 12d ago First seen · 114 lines · 158 tokens per session scan A 880ccb115383

Subscribe to this mod's changes

couchbase-magma is a skill published in the GitHub repository celticht32/Couchbase-Skills-for-Claude.ai (4 stars, last pushed 2mo ago), licensed MIT. It adds 158 tokens to every session and 1,501 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.

davila7/claude-code-templates · 35 tokens

chroma

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…

davila7/claude-code-templates · 63 tokens

db-seed

Generate database seed scripts with realistic sample data. Reads Drizzle schemas or SQL migrations, respects foreign key ordering, produces idempotent TypeScript or SQL seed files. Handles D1 batch limits, unique constraints, and domain-appropriate data. Use when populating dev/demo/test databases. Triggers: 'seed…

jezweb/claude-skills · 96 tokens

d1-drizzle-schema

Generate Drizzle ORM schemas for Cloudflare D1 databases with correct D1-specific patterns. Produces schema files, migration commands, type exports, and DATABASESCHEMA.md documentation. Handles D1 quirks: foreign keys always enforced, no native BOOLEAN/DATETIME types, 100 bound parameter limit, JSON stored as TEXT.…

jezweb/claude-skills · 90 tokens

d1-migration

Cloudflare D1 migration workflow: generate with Drizzle, inspect SQL for gotchas, apply to local and remote, fix stuck migrations, handle partial failures. Use when running migrations, fixing migration errors, or setting up D1 schemas.

jezweb/claude-skills · 53 tokens

qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

davila7/claude-code-templates · 46 tokens