couchbase-fts

couchbase-fts is a skill for Claude Code, Codex from celticht32/Couchbase-Skills-for-Claude.ai. It costs 208 tokens per session (1,646 once invoked), scanned A, original, MIT.

A guide to Couchbase Full Text Search and vector search. Full Text Search finds documents by words and phrases; vector search finds documents with similar meaning or content.

In plain words
What is it for?
Creating and tuning search indexes, configuring language analyzers, searching by phrases or locations, ranking results, using semantic search, and combining text with vector search.
Why use it?
It helps design indexes and queries when basic database indexes are not enough for text, similarity, or location-based searches.

Skill for Claude CodeCodex

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

Good fit Creating and tuning search indexes, configuring language analyzers, searching by phrases or locations, ranking results, using semantic search, and combining text with vector search.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-fts"><img src="https://agentmods.dev/badge/skills/celticht32/couchbase-skills-for-claude.ai/couchbase-fts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 208 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,646 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 $0.00208 $0.01646
Opus 5 $0.00104 $0.00823
Sonnet 5 $0.00042 $0.00329
Haiku 4.5 $0.00021 $0.00165

Measured 12d ago against content hash d79b560be5ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

couchbase-fts 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-fts/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A skill for designing and operating Couchbase FTS and vector search indexes. Distinct from:

  • couchbase-sqlpp-tuning — SQL++ / GSI index design (not Search service)
  • couchbase-data-modeling — document shape decisions that affect what FTS can index
  • couchbase-mcp — calling the actual cb_fts_search, admin_fts_*, and admin_vector_index_* tools

If the conversation is "I need to search text / find similar documents / search by location," this is the right skill.

When this skill applies

  • "How do I do full-text search in Couchbase?"
  • "How do I build an FTS index?"
  • "Why isn't my FTS query matching what I expect?"
  • "How do I add fuzzy / wildcard / phrase search?"
  • "How do I search by geo-distance?"
  • "How do I implement vector / semantic / kNN search?"
  • "How do I combine text search with vector search (hybrid)?"
  • "What analyzer should I use for [language]?"
  • "How do I boost certain fields?"
  • "What are FTS synonyms and when should I use them?"
  • "How do I size FTS / vector index memory?"

Pick the right reference

Question Read
"How do I design an FTS index — mappings, analyzers, type fields?" references/index-design.md
"How do I write FTS queries — match, phrase, fuzzy, wildcard, conjunction, geo?" references/query-types.md
"Analyzers, tokenizers, token filters — how do they work, which to pick?" references/analyzers.md
"Vector search — kNN, hybrid search, index design for embeddings?" references/vector-search.md
"FTS synonyms (8.x) — what they are, how to create, when to use?" references/synonyms.md
"FTS is slow / results are wrong / index not updating — how to debug?" references/troubleshooting.md

Three core principles

Principle 1 — The index definition determines everything. FTS doesn't infer what to index from the document. If a field isn't mapped (or dynamic mapping is off), FTS ignores it. Get the index definition right before debugging queries. The most common FTS failure mode is "the field isn't indexed."

Read the full file on GitHub · 89 lines

Files

What ships with it

6 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.

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 · 89 lines · 208 tokens per session scan A d79b560be5ed

Subscribe to this mod's changes

couchbase-fts is a skill published in the GitHub repository celticht32/Couchbase-Skills-for-Claude.ai (4 stars, last pushed 2mo ago), licensed MIT. It adds 208 tokens to every session and 1,646 once invoked, about $0.0010 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.