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 cb-analytics-admingit 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/cb-analytics-admin)<a href="https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/cb-analytics-admin"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/cb-analytics-admin/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/cb-analytics-admin"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/cb-analytics-admin.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 | $0.00075 | $0.00836 |
| Opus 5 | $0.00037 | $0.00418 |
| Sonnet 5 | $0.00015 | $0.00167 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
cb-analytics-admin 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cb-analytics-admin — 91% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analytics service admin
You have 7 tools for runtime management.
Status snapshot (read-only, safe)
get_service_status(cluster)— overall service state, replica lag, authorised node listget_ingestion_status(cluster)— per-link ingestion state, pending opsget_active_requests(cluster)— what's running right nowget_completed_requests(client_context_id=None, cluster)— recent history; passclient_context_idto filter to one request
Diagnostic workflow
When a user says "queries are slow" or "ingestion looks stuck":
get_service_status— is the service even healthy? WatchccRevLag(replication lag).get_ingestion_status— for each link, look atpendingOperations. A non-zero pending count after a quiet period usually means a stuck link.get_active_requests— long-running queries appear here withelapsedTime. Anything over a few seconds is suspect.get_completed_requests— look for a pattern of errors or unusually long durations.
Destructive operations (use with care)
cancel_request(client_context_id, cluster)— abort one in-flight query. Get the id fromget_active_requests.restart_node(cluster)— restart only the Analytics process on the local node. May briefly disrupt queries routed to that node.restart_service(cluster)— cluster-wide Analytics restart. All active queries fail. Don't suggest this lightly; warn the user.
Confirmation patterns
When the user asks to cancel or restart anything, always confirm by naming what you're about to do, with the specific request id or cluster name. Example:
Cancel request
cb-12345on clusterprod? This will return an error to whichever client issued it.
After they confirm, run the tool and report success or failure based on
the returned ok field.
What to avoid
- Don't restart the service to "fix" a slow query — try cancelling it first.
- Don't call
cancel_requeston aclient_context_idthat's already completed; it's a no-op but generates a confusing error. - Don't poll
get_active_requestsaggressively (e.g. every second). Once per few seconds is fine.
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 · 91 lines · 75 tokens per session scan A ddc2c6d00fcd
cb-analytics-admin is a skill published in the GitHub repository celticht32/Couchbase-Skills-for-Claude.ai (4 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 836 once invoked, about $0.0004 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
anki-cards
Distill conversations into Anki flashcards exported as a TSV file. Use this skill whenever the user mentions Anki, flashcards, spaced repetition cards, "make cards from this", "distill into cards", "I want to memorize this", "create review cards", or any variation of turning conversation content into study material.…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
gepetto
Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
crewai
Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative…