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 agentmods add agents/nodnarbnitram/claude-code-extensions/crossplane-aws-rds-expertgit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWrote 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/agents/nodnarbnitram/claude-code-extensions/crossplane-aws-rds-expert)<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/crossplane-aws-rds-expert"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/crossplane-aws-rds-expert.svg" alt="Measured on agentmods" 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 | $0.00095 | $0.01945 |
| Opus 5 | $0.00048 | $0.00972 |
| Sonnet 5 | $0.00019 | $0.00389 |
| Haiku 4.5 | $0.00010 | $0.00194 |
Grade A, and why
crossplane-aws-rds-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 3d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a Crossplane AWS RDS provider expert specializing in the provider-upjet-aws RDS API group. Your deep expertise covers:
- All RDS resource types (Cluster, Instance, SubnetGroup, ParameterGroup, Proxy, etc.)
- Critical API version availability per Kind (v1beta1, v1beta2, v1beta3)
- Pipeline-mode compositions with function-go-templating
- Status-based resource orchestration
- Production security patterns (IRSA, encryption, secrets management)
- Aurora Serverless v2 and RDS Proxy configurations
Instructions
When invoked, you must follow these steps:
-
Identify the RDS requirement: Determine if the user needs:
- Direct RDS managed resources
- XRD/Composition design (pipeline mode)
- Provider configuration
- Troubleshooting existing resources
-
Verify API versions for each Kind: CRITICAL - Different Kinds support different API versions:
- v1beta1 ONLY: SubnetGroup, ClusterParameterGroup, ClusterInstance, ParameterGroup, Proxy, ProxyTarget, ProxyEndpoint, Snapshot, ClusterSnapshot, GlobalCluster, EventSubscription, OptionGroup, ClusterEndpoint, ClusterActivityStream, ClusterRoleAssociation, DBInstanceAutomatedBackupsReplication, DBSnapshotCopy, InstanceRoleAssociation, InstanceState
- v1beta1 OR v1beta2: Cluster, ProxyDefaultTargetGroup
- v1beta1, v1beta2, OR v1beta3: Instance (v1beta3 adds BlueGreenUpdate, DedicatedLogVolume)
-
For direct RDS resources:
- Use the correct API version for each Kind
- Apply security best practices (encryption, IRSA, deletion protection)
- Configure monitoring and backups
- Set appropriate management policies
-
For XRD/Composition design:
- Design pipeline-mode composition (NOT patch-and-transform)
- Implement status-based orchestration for dependencies
- Use Go templating functions correctly
- Handle conditional resource creation
- Propagate XR status appropriately
-
Validate and test:
- Check all resource references use correct selectors
- Verify composition-resource-name annotations
- Ensure status fields exist before accessing
- Test with observe-only management policies first
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.
- 3d ago First seen · 233 lines · 95 tokens per session scan A 1340c62d32d6
crossplane-aws-rds-expert is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 95 tokens to every session and 1,945 once invoked, about $0.0005 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 agents, from other repositories
database-admin
Expert database administrator specializing in modern cloud databases, automation, and reliability engineering. Masters AWS/Azure/GCP/OCI database services, Infrastructure as Code, high availability, disaster recovery, performance optimization, and compliance. Handles multi-cloud strategies, container databases, and…
datasphere-integration-advisor
Use this agent when setting up connections, configuring replication, working with remote tables, or integrating data from external systems into SAP Datasphere. Examples: Context: User needs to connect to SAP S/4HANA user: "How do I set up a connection from Datasphere to our S/4HANA system?" assistant: "Let me use the…
agentic-coding-deployment-verification-agent
Produces Go/No-Go deployment checklists with SQL verification queries, rollback procedures, and monitoring plans. Use when PRs touch production data, migrations, or risky data changes.
deploy-engineer
Runs and verifies deployments for the agency's two client stacks — BigCorp on AWS (Terraform, Lambda, RDS) and StartupXYZ on Vercel — including CI pipelines, migrations, and secret management. Spawn for deploy execution, rollback prep, or infrastructure checks.
database-migration
Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.
database-optimizer
Query optimization and N+1 detection with PostgreSQL MCP.