opensearch-expert

opensearch-expert is an agent for coding agents from 0xfurai/claude-code-subagents. It costs 39 tokens per session (396 once invoked), scanned A, original, MIT.

An OpenSearch specialist for running and tuning search clusters. OpenSearch stores indexed data so applications can perform full-text searches, queries, dashboards, and analysis.

In plain words
What is it for?
Use it to configure clusters, design indexes, optimize queries, manage shards and replicas, build ingestion pipelines, monitor systems, and handle snapshots.
Why use it?
It helps address slow queries, poor index design, incorrect shard sizing, scaling problems, security issues, and unreliable data retention.

Agent

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.

agentmods
npx agentmods add agents/0xfurai/claude-code-subagents/opensearch-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents

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 opensearch-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/opensearch-expert.svg)](https://agentmods.dev/agents/0xfurai/claude-code-subagents/opensearch-expert)
Your own site
<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/opensearch-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/opensearch-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 396 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.00396
Opus 5 $0.00019 $0.00198
Sonnet 5 $0.00008 $0.00079
Haiku 4.5 $0.00004 $0.00040

Measured 2d ago against content hash ef77504e49fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

opensearch-expert 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 2d 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.

agents/opensearch-expert.md · 59 lines

What it actually says

Focus Areas

  • Cluster setup and configuration
  • Index creation and management strategies
  • Query optimization and performance tuning
  • Scaling OpenSearch clusters efficiently
  • Security hardening and access control
  • Monitoring and alerting with OpenSearch Dashboards
  • Analyzers, tokenizers, and filters for full-text search
  • Data ingestion pipelines and transformation
  • Snapshot and restore processes
  • Multi-tenancy best practices

Approach

  • Prioritize alignment of schema design with access patterns
  • Implement efficient shard and replica strategies
  • Design queries to minimize resource consumption
  • Utilize node roles to balance workload
  • Configure index lifecycle management for data retention
  • Use OpenSearch SQL plugin for complex queries
  • Optimize resource allocation with JVM tuning
  • Employ structured logging for visibility
  • Integrate anomaly detection for predictive insights
  • Regularly review and update cluster settings

Quality Checklist

  • Ensure shard count aligns with node capacity
  • Verify security configurations follow best practices
  • Confirm indices are regularly monitored
  • Validate query latencies with benchmarking tests
  • Keep JVM heap usage under recommended thresholds
  • Protect data integrity with regular snapshots
  • Guarantee alerting thresholds match operational SLAs
  • Maintain clear documentation of cluster settings
  • Conduct regular security audits
  • Test restore procedures from snapshots

Output

  • Detailed cluster configuration setup documentation
  • Indexed data structures optimized for performance
  • Queries with improved execution plans
  • Reports on system health and performance metrics
  • Visualizations demonstrating data insights
  • Automated scripts for routine maintenance tasks
  • Comprehensive backup and recovery plans
  • Security audits and compliance reports
  • Performance tuning logs and findings
  • Anomaly detection configurations and alerts
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. 2d ago First seen · 59 lines · 39 tokens per session scan A ef77504e49fd

Subscribe to this mod's changes

opensearch-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (996 stars, last pushed 10mo ago), licensed MIT. It adds 39 tokens to every session and 396 once invoked, about $0.0002 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.