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-capellagit 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-capella)<a href="https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-capella"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-capella/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-capella"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-capella.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 | $0.00180 | $0.00725 |
| Opus 5 | $0.00090 | $0.00362 |
| Sonnet 5 | $0.00036 | $0.00145 |
| Haiku 4.5 | $0.00018 | $0.00072 |
Grade A, and why
couchbase-capella 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Couchbase Capella
A skill for provisioning and configuring Couchbase Capella deployments — from free tier through production, covering networking, credentials, and application connectivity.
Distinct from:
couchbase-sizing— Capella tier selection mathcouchbase-security-hardening— TLS, RBAC, and audit configuration once the cluster is runningcouchbase-backup-restore— Capella backup and restore
When this skill applies
- "How do I create a Capella cluster?"
- "How do I connect my app to Capella?"
- "What's the difference between database credentials and admin credentials?"
- "How do I set up allowed CIDRs / private networking?"
- "How do I set up VPC peering or PrivateLink with Capella?"
- "What are Capella orgs, projects, and clusters?"
- "How do I set up Capella App Services?"
- "Free tier vs paid — what are the differences?"
Pick the right reference
| Question | Read |
|---|---|
| "Getting started — free tier, org/project structure, first cluster" | references/getting-started.md |
| "Networking — allowed CIDRs, VPC peering, PrivateLink" | references/networking.md |
| "Credentials — database users vs admin, connection strings" | references/credentials.md |
Key Capella concepts
Organization → Project → Cluster is the hierarchy. Everything lives under an org. Projects group clusters by environment (dev, staging, prod). Clusters are the actual Couchbase deployments.
Database credentials ≠ cluster admin credentials. The admin credentials (used in the Capella UI) are for management only and should never be in your application code. Database credentials (created per cluster, scoped to buckets and roles) are what applications use. Always use database credentials for SDK connections.
Allowed CIDRs are IP allowlists at the cluster level. Your application's outbound IP(s) must be in the allowlist before connections are accepted. For production, use private networking (VPC peering or PrivateLink) instead of public-internet allowed CIDRs.
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.
- 12d ago First seen · 50 lines · 180 tokens per session scan A d5a5163ab956
couchbase-capella is a skill published in the GitHub repository celticht32/Couchbase-Skills-for-Claude.ai (4 stars, last pushed 2mo ago), licensed MIT. It adds 180 tokens to every session and 725 once invoked, about $0.0009 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
planning-disaster-recovery
Design and implement disaster recovery strategies with RTO/RPO planning, database backups, Kubernetes DR, cross-region replication, and chaos engineering testing. Use when implementing backup systems, configuring point-in-time recovery, setting up multi-region failover, or validating DR procedures.
ray-train
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention.
ai-persistence/build-cloudflare-artifact-store
Use when a Cloudflare Worker needs durable byte storage for TanStack AI generated media (images, audio, video, transcripts) — writes a BlobStore backed by R2 and an ArtifactStore backed by D1, composes them onto the generation persistence so withGenerationPersistence persists artifact bytes, and serves them back from…