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 j4flmao/agent-skills --skill search-enginegit clone --depth 1 https://github.com/j4flmao/agent-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/j4flmao/agent-skills/search-engine)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/search-engine"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/search-engine/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/j4flmao/agent-skills/search-engine"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/search-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00127 | $0.06113 |
| Opus 5 | $0.00063 | $0.03057 |
| Sonnet 5 | $0.00025 | $0.01223 |
| Haiku 4.5 | $0.00013 | $0.00611 |
Grade A, and why
data-search-engine 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 6d 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 — 543 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Search Engine
Purpose
Design and configure search engine clusters for full-text search, log analytics, and real-time data exploration with proper indexing, query design, and cluster management.
Agent Protocol
Trigger
Exact user phrases: "Elasticsearch", "OpenSearch", "Solr", "search engine", "full-text search", "inverted index", "indexing", "search analytics", "aggregation", "cluster management", "shard routing", "mapping", "analysis", "tokenization", "ILM", "index lifecycle".
Input Context
Before activating, verify:
- Search platform (Elasticsearch, OpenSearch, Solr)
- Data types (text, structured, geo, time-series)
- Query patterns (full-text search, faceted navigation, aggregations, autocomplete)
- Indexing volume (docs/sec, total doc count, index size)
- Cluster topology (node count, hardware, cloud/on-prem)
- Replication and HA requirements
- Retention and lifecycle policies
Output Artifact
Search index mapping with analyzers, query templates, aggregation pipelines, and cluster configuration as JSON and YAML.
Response Format
// Index mapping with analyzers
// Search query template
// Aggregation pipeline
# Cluster configuration
# Index lifecycle policy
# Shard allocation rules
No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick.
Completion Criteria
- Index mapping with proper field types, analyzers, and multi-fields
- Search templates for common query patterns (match, bool, term, fuzzy)
- Aggregation pipeline for faceted navigation and analytics
- Cluster topology designed (node roles, shard count, replica count)
- Index lifecycle policy configured (hot, warm, cold, delete phases)
- Performance tuning applied (refresh interval, merge settings, thread pools)
- OpenSearch-specific features considered if applicable
Max Response Length
300 lines of configuration and queries.
Workflow
Step 1: Index Mapping Design
Explicit mapping required — never use dynamic mapping for production. Define field types: text for full-text search with analyzer, keyword for exact match/aggregations/sorting, integer/long/double for numeric, date with format, geo_point for location, nested for arrays of objects (preserves independence), flattened for semi-structured metadata, object for simple JSON.
What ships with it
8 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.
- references/elasticsearch-architecture.md 3.7 KB
- references/modern-search-engines.md 4.7 KB
- references/search-aggregation.md 4.0 KB
- references/search-engine-distributed-architecture.md 35 KB
- references/search-engine-optimization.md 3.3 KB
- references/search-engine-ranking-relevance.md 32 KB
- references/search-operations.md 841 B
- references/search-relevance-tuning.md 952 B
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.
- 6d ago First seen · 543 lines · 127 tokens per session scan A 99dc1d669944
data-search-engine is a skill published in the GitHub repository j4flmao/agent-skills (22 stars, last pushed 3d ago), licensed MIT. It adds 127 tokens to every session and 6,113 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
elasticsearch-expert
Expert-level Elasticsearch, search, ELK stack, and full-text search. Use when the user mentions search, ELK, Logstash, Kibana, or full text search.
kg-modality-sql
Run SQL against the engine over real database wire protocols — Postgres (pgwire), MySQL, MSSQL/TDS, and the SQLite NDJSON endpoint — so psql/DBeaver/BI/ORMs connect to the engine as if it were their existing database (epistemic-graph owns the wire). Use for SELECT/joins/ aggregates/window/CTE and INSERT/UPDATE/DELETE…
salvo-database
Integrate databases with Salvo using SQLx, Diesel, SeaORM, or other ORMs. Use for persistent data storage and database operations.
vector-db
Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies.
elasticsearch
Elasticsearch expert for queries, mappings, aggregations, index management, and cluster operations.
build-with-tinybase
Scaffold, extend, and verify reactive local-first JavaScript or TypeScript applications with TinyBase. Use when choosing TinyBase for in-memory tabular or key-value state, generating an app with create-tinybase, adding schemas or UI bindings, configuring browser or database persistence, configuring MergeableStore…