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.
git clone --depth 1 https://github.com/GoranErhartic/cursor-development-rulesWrote 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/rules/goranerhartic/cursor-development-rules/opensearch)<a href="https://agentmods.dev/rules/goranerhartic/cursor-development-rules/opensearch"><img src="https://agentmods.dev/badge/rules/goranerhartic/cursor-development-rules/opensearch/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/rules/goranerhartic/cursor-development-rules/opensearch"><img src="https://agentmods.dev/badge/rules/goranerhartic/cursor-development-rules/opensearch.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 | $0.00017 | $0.00470 |
| Opus 5.5 | $0.00007 | $0.00188 |
| Sonnet 5.5 | $0.00003 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
opensearch 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 1mo 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.
What it actually says
OpenSearch Patterns
Overview
OpenSearch provides full-text search and geo queries. Lambda integration requires memory-efficient bulk operations and connection reuse.
Client
- Use
@opensearch-project/opensearchwithAwsSigv4Signerfor auth; singleton client;node: process.env.OPENSEARCH_ENDPOINT; close client on cold start teardown if needed - Set
maxRetries,requestTimeout; useaossservice for OpenSearch Serverless
Index and Mapping
- Define mapping (keyword vs text, geo_point for location); use custom analyzers for address/text search
- Create index with
client.indices.create({ index, body: mapping }); checkexistsbefore create - Use environment-based index name
Bulk Indexing
- Bulk API: Build body as array of
{ index: { _index, _id } }and{ ...doc }pairs; chunk (e.g. 500–1000 docs) to avoid memory/timeout - Memory: Stream or batch from DynamoDB Streams; do not load full result set into memory
- Handle partial failures: check
response.body.itemsfor per-item errors; retry failed items or log and continue
Search Queries
- Full-text:
match,match_phrase,multi_match; usekeywordfor exact filters - Geo:
geo_distance,geo_bounding_boxwithlocationasgeo_point; distance in km/mi - Compound:
boolwithmust,filter,should,must_not;filterfor non-scoring - Pagination:
from/sizeorsearch_afterfor deep pagination
Conventions
- Single client per Lambda; chunk bulk ops; use filters to reduce result size; avoid large
sizein one request - Include correlationId/traceId in logs for debugging
Anti-Patterns
- Loading entire dataset into memory; unbounded bulk size; scanning without filters; ignoring bulk item errors
See also: dynamodb-streams.mdc, logging-setup.mdc
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.
- 1mo ago First seen · 45 lines · 17 tokens per session scan A 33d1e2637a4a
opensearch is a cursor rule published in the GitHub repository GoranErhartic/cursor-development-rules (19 stars, last pushed 7mo ago), licensed MIT. It adds 17 tokens to every session and 470 once invoked, about $0.0001 per session on Opus 5.5. 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 cursor rules, from other repositories
ehs-ims-conventions
EHS IMS app — RBAC, data layer, tRPC, migrations, AI boundaries.
rulesforconvex
description: Convex guidelines globs: alwaysApply: true.
startup-migration-bounded-work
Production djangostartup migrate must be bounded; never run makemigrations in production.
redis_rate_limiting
Complete guide for implementing Redis-based rate limiting with authentication troubleshooting and FastAPI integration.
schema
Scalable and secure schema design patterns for relational databases, NoSQL, and APIs. / TR: İlişkisel veri tabanları, NoSQL ve API'ler için ölçeklenebilir ve güvenli şema tasarım kalıpları.
java-springboot-jpa-cursorrules-prompt-file
description: "Cursor rules for Java development with Springboot and JPA integration." globs: / alwaysApply: false.