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-performance-tuninggit 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-performance-tuning)<a href="https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-performance-tuning"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-performance-tuning/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-performance-tuning"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-performance-tuning.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 | $0.00166 | $0.00882 |
| Opus 5 | $0.00083 | $0.00441 |
| Sonnet 5 | $0.00033 | $0.00176 |
| Haiku 4.5 | $0.00017 | $0.00088 |
Grade A, and why
couchbase-performance-tuning 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Couchbase Performance Tuning
A skill for diagnosing and fixing performance problems at the cluster level — KV latency, throughput limits, disk I/O, compaction, connection saturation, and thread pool configuration.
Distinct from:
couchbase-sqlpp-tuning— SQL++ query tuning (index design, EXPLAIN plans, anti-patterns)couchbase-observability— what metrics to monitor and alert thresholdscouchbase-sizing— how much capacity to provision in the first place
If the question is "my queries are slow," go to couchbase-sqlpp-tuning. If the question is "my cluster is right-sized but everything is slow," this is the right skill.
When this skill applies
- "KV get/set latency is higher than expected"
- "Throughput isn't reaching the hardware's capability"
- "Compaction is killing performance"
- "We're hitting connection limits"
- "Rebalance is taking too long"
- "High CPU on Couchbase nodes but no obvious cause"
- "Disk I/O is spiking unpredictably"
- "DCP consumers are falling behind"
Pick the right reference
| Question | Read |
|---|---|
| "KV latency / throughput — diagnosis and tuning" | references/kv-tuning.md |
| "Compaction — autocompaction settings, impact, tuning" | references/compaction.md |
| "Connection limits, thread pools, OS-level tuning" | references/system-tuning.md |
The diagnosis sequence
Before tuning anything, locate the actual bottleneck:
-
Is it memory? Check
ep_mem_used / ep_mem_high_wat. If > 85%, ejections are happening and reads go to disk. Fix: add RAM, add nodes, or reduce working set. -
Is it disk I/O? Check
ep_bg_fetched(reads going to disk) andep_diskqueue_drainvsep_diskqueue_fill. Fix: faster storage, Magma (if on 8.0), or reduce write rate. -
Is it CPU? Check per-node CPU utilization. Which service is consuming it? Query and Index are CPU-heavy; KV should be low-CPU unless you're near capacity. Fix: dedicated nodes per service, or add nodes.
-
Is it network? Check
bytes_sentandbytes_receivedper node against the node's NIC capacity. Fix: higher-bandwidth instances, or reduce replication/XDCR traffic.
What ships with it
3 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 · 61 lines · 166 tokens per session scan A cfc26f058094
couchbase-performance-tuning is a skill published in the GitHub repository celticht32/Couchbase-Skills-for-Claude.ai (4 stars, last pushed 2mo ago), licensed MIT. It adds 166 tokens to every session and 882 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.
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.
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…
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…
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.…
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.
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.