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 sandeepmvl/rails-skills --skill 37-rails-searchgit clone --depth 1 https://github.com/sandeepmvl/rails-skillsWrote 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/sandeepmvl/rails-skills/37-rails-search)<a href="https://agentmods.dev/skills/sandeepmvl/rails-skills/37-rails-search"><img src="https://agentmods.dev/badge/skills/sandeepmvl/rails-skills/37-rails-search/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/sandeepmvl/rails-skills/37-rails-search"><img src="https://agentmods.dev/badge/skills/sandeepmvl/rails-skills/37-rails-search.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 | $0.00135 | $0.02813 |
| Opus 5 | $0.00068 | $0.01406 |
| Sonnet 5 | $0.00027 | $0.00563 |
| Haiku 4.5 | $0.00014 | $0.00281 |
Grade A, and why
rails-search 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rails Search
Three tiers. Use the cheapest one that solves the problem. Most Rails apps never need Elasticsearch — Postgres + pg_search gets you to millions of rows with good UX. AI agents reach for ES by default; this skill pushes back.
The opinion
Default:
pg_searchwith PostgreSQL tsvector + pg_trgm. Step up to Meilisearch when you need typo tolerance, autocomplete, and faceted UX. Reach for Elasticsearch / OpenSearch only when you genuinely need clustered, sharded, analytics-grade search at billion-row scale. Usesearchkickas a Rails-idiomatic wrapper around either Elasticsearch or OpenSearch. Always index in the background, never inline.
Why this order:
- pg_search uses your existing database. No new infra. No sync drift.
- Meilisearch is a single-binary Rust server. Smaller than ES, sub-50ms queries, typo tolerance built-in.
- ES/OpenSearch is the right tool at scale but operationally expensive — cluster management, JVM tuning, mapping migrations.
Tier 1: pg_search (default)
Setup
# Gemfile
gem "pg_search"
# db/migrate/...
class AddPgTrgm < ActiveRecord::Migration[8.0]
def change
enable_extension "pg_trgm" # for fuzzy / similarity
end
end
Pattern 1: Per-model search
class Post < ApplicationRecord
include PgSearch::Model
pg_search_scope :search_full_text,
against: { title: "A", body: "B" }, # weights — A is highest
using: {
tsearch: { prefix: true, dictionary: "english" },
trigram: { threshold: 0.3 }
}
end
Post.search_full_text("rails search")
# → ranked posts matching either by tsvector or trigram similarity
against: { title: "A", body: "B" } — Postgres ts_rank weights. A > B > C > D. Title matches rank higher than body matches.
Pattern 2: Multi-search across models
class Post < ApplicationRecord
include PgSearch::Model
multisearchable against: [:title, :body]
end
class User < ApplicationRecord
include PgSearch::Model
multisearchable against: [:name, :bio]
end
PgSearch.multisearch("alice")
# → ActiveRecord::Relation of PgSearch::Document
# Each document has searchable_type ("Post" or "User") and searchable_id.
What ships with it
1 file 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 · 353 lines · 135 tokens per session scan A cd783292f4e3
rails-search is a skill published in the GitHub repository sandeepmvl/rails-skills (21 stars, last pushed 3mo ago), licensed MIT. It adds 135 tokens to every session and 2,813 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
azure-postgres-ts
Connect to Azure Database for PostgreSQL Flexible Server from Node.js/TypeScript using the pg (node-postgres) package. Use for PostgreSQL queries, connection pooling, transactions, and Microsoft Entra ID (passwordless) authentication. Triggers: "PostgreSQL", "postgres", "pg client", "node-postgres", "Azure PostgreSQL…
butterbase
AI-native, open-source backend-as-a-service with a built-in Model Context Protocol server. Postgres, auth, storage, functions, AI gateway.
supabase
Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies…
supabase-cli
This skill should be used when user asks to "use supabase CLI", "supabase init", "supabase start", "run migrations", "deploy edge functions", "manage Supabase project", or works with the supabase command-line tool for local development and project management.
supabase-js
This skill should be used when user asks to "use supabase-js", "query Supabase database", "supabase auth", "supabase storage", "supabase realtime", "supabase edge functions", or works with the @supabase/supabase-js JavaScript/TypeScript SDK.
supabase-node
Express/Hono with Supabase and Drizzle ORM.