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-mobilegit 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-mobile)<a href="https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-mobile"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-mobile/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-mobile"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-mobile.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 | $0.00184 | $0.01352 |
| Opus 5 | $0.00092 | $0.00676 |
| Sonnet 5 | $0.00037 | $0.00270 |
| Haiku 4.5 | $0.00018 | $0.00135 |
Grade A, and why
couchbase-mobile 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Couchbase Mobile
A skill for designing and building mobile and edge applications with Couchbase Lite + Sync Gateway / Capella App Services — offline-first sync, channel-based access control, conflict resolution, and mobile-specific patterns.
Distinct from:
couchbase-xdcr— server-to-server replication between Couchbase clusterscouchbase-app-integration— server-side SDK integration (Python, Java, Node.js, etc.)couchbase-capella— Capella cluster provisioning (App Services runs on top of a Capella cluster)
If the conversation is "I'm building a mobile app / offline-first app / IoT device that needs to sync with Couchbase," this is the right skill.
When this skill applies
- "How do I sync data to an iOS / Android app?"
- "How do I build an offline-first app with Couchbase?"
- "What's Couchbase Lite?"
- "How does Sync Gateway work?"
- "How do I set up Capella App Services?"
- "How do I control which users see which documents?"
- "How do I handle conflicts in mobile sync?"
- "How do I do peer-to-peer sync between devices?"
- "Can I use vector search in Couchbase Lite?"
Pick the right reference
| Question | Read |
|---|---|
| "Architecture — Lite vs Sync Gateway vs App Services, when to use which" | references/architecture.md |
| "Sync function — channels, access control, routing documents to users" | references/sync-function.md |
| "Couchbase Lite — replicator config, conflict resolution, queries" | references/couchbase-lite.md |
Three core principles
Principle 1 — Channel-based access is the security model. Sync Gateway / App Services control data access through channels. A document is routed to one or more channels by the sync function; a user has access to a set of channels. Users only receive documents in channels they have access to. There is no other row-level security mechanism — if you need per-document access control, you need per-document or per-group channels.
Principle 2 — Offline-first means conflicts are inevitable. When two devices edit the same document while offline, both changes are valid locally. When they sync, a conflict occurs. Couchbase Lite resolves conflicts automatically (last-write-wins by default) or via a custom conflict resolver. Design your documents assuming conflicts will happen — use additive updates (event logs, append-only fields) over destructive in-place updates where possible.
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 · 90 lines · 184 tokens per session scan A 8371a9cdb363
couchbase-mobile is a skill published in the GitHub repository celticht32/Couchbase-Skills-for-Claude.ai (4 stars, last pushed 2mo ago), licensed MIT. It adds 184 tokens to every session and 1,352 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
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
suede-aso
Suede-owned app-store optimization discipline for keyword fields, titles, subtitles, descriptions, screenshots, ratings context, and competitor listing audits. Use when improving App Store or Google Play visibility or listing conversion from a live app URL and current console evidence. NOT FOR: building or releasing…
android-app-factory
Suede Labs Android app factory: plan, build, test, and release a production-grade native Android app from a product idea through Google Play. Use for requests to create, ship, submit, monetize, or modernize an Android app. Covers Kotlin and Jetpack Compose architecture, API-level policy verification, accessibility…
suede-play-release
Suede Labs Google Play delivery skill: ship an Android release end to end from the agent interface, without opening the Play Console. Set up credentials, upload an AAB, promote between tracks, stage or complete a rollout, push per-locale release notes, and prove against the Play Developer API what is actually live.…
persistence-setup
Generates SwiftData or CoreData persistence layer with optional iCloud sync. Use when user wants to add local storage, data persistence, or cloud sync.
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…