Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/selvarajmurugesan90/ops-engineering-skillsnpx agentmods add skills/selvarajmurugesan90/ops-engineering-skills/arangodb-multi-model-database-operationsWrote 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/selvarajmurugesan90/ops-engineering-skills/arangodb-multi-model-database-operations)<a href="https://agentmods.dev/skills/selvarajmurugesan90/ops-engineering-skills/arangodb-multi-model-database-operations"><img src="https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/arangodb-multi-model-database-operations/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/selvarajmurugesan90/ops-engineering-skills/arangodb-multi-model-database-operations"><img src="https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/arangodb-multi-model-database-operations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 141 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 271 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00132 | $0.03937 |
| Opus 5 | $0.00066 | $0.01969 |
| Sonnet 5 | $0.00026 | $0.00787 |
| Haiku 4.5 | $0.00013 | $0.00394 |
Grade A, and why
arangodb-multi-model-database-operations scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -u <USER>:<PASSWORD> http://<COORDINATOR_HOST>:8529/_admin/cluster/health How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ArangoDB Multi-Model Database Operations
Purpose
ArangoDB's distinguishing architectural bet is multi-model in one engine: document collections, key-value access, and graph data (via edge collections connecting document vertices) all live in the same database, queried through a single language — AQL (ArangoQL) — rather than requiring separate document, graph, and key-value systems stitched together at the application layer. This is a materially different trade-off than a graph-only engine like neo4j-graph-database-operations: ArangoDB is the right choice when a workload genuinely needs both general document storage and graph traversal against the same data without operating two databases, at the cost of graph traversal performance that (for very deep or very high-fan-out traversals) doesn't match a purpose-built graph engine's native storage layout. This skill covers AQL fundamentals for ops, collection-type selection, and cluster configuration (coordinators, DB-servers, the Raft-based agency) — the operational core for running ArangoDB reliably at scale.
When to use
- Deciding whether a new collection should be a document collection, an edge collection (for graph relationships), or accessed purely as key-value, and modeling accordingly.
- Writing or debugging an AQL query, especially a graph traversal
(
FOR v, e, p IN ... GRAPH) that's slow or returns unexpected results. - Setting up or troubleshooting an ArangoDB cluster: coordinators, DB-servers (the actual data-holding shards), and the agency (Raft- based cluster metadata/consensus layer).
- Choosing sharding keys for a document collection, or a graph's vertex collections, to avoid an unevenly loaded cluster.
- Evaluating ArangoDB against running separate document/graph/key-value systems for a workload that genuinely spans all three access patterns.
Prerequisites & environment
- ArangoDB 3.11+ assumed for the AQL syntax below; note that SmartGraphs (sharded graphs with locality-aware placement, an Enterprise Edition feature) require the Enterprise Edition, while standard (non-Smart) graphs and cluster mode itself are available in the Community Edition.
- For cluster mode: at least 3 agency nodes (Raft consensus for cluster metadata — the same odd-quorum requirement as any Raft-based system elsewhere in this repo), at least 1 coordinator (stateless query-routing/aggregation layer that clients connect to), and at least 2 DB-servers per shard's replication factor (the nodes that actually store shard data).
arangosh(the ArangoDB shell) or the HTTP API for administrative operations; a user with theAdministratedatabase access level for collection/index/graph management.- Familiarity with the workload's actual access pattern (pure document lookups vs. genuine multi-hop graph traversal vs. a mix) before choosing collection types and sharding keys — like Cassandra partition-key design, this is a decision that's expensive to change after data and shard layout are established.
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.
- 11d ago First seen · 333 lines · 132 tokens per session scan A 7de5c2b47f01
arangodb-multi-model-database-operations is a skill published in the GitHub repository selvarajmurugesan90/ops-engineering-skills (38 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 132 tokens to every session and 3,937 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…