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 skills/oghie/skillsets/data-architect-engineeringnpx skills add oghie/skillsets --skill data-architect-engineeringgit clone --depth 1 https://github.com/oghie/skillsetsWrote 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/oghie/skillsets/data-architect-engineering)<a href="https://agentmods.dev/skills/oghie/skillsets/data-architect-engineering"><img src="https://agentmods.dev/badge/skills/oghie/skillsets/data-architect-engineering.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 | $0.00098 | $0.03325 |
| Opus 5 | $0.00049 | $0.01663 |
| Sonnet 5 | $0.00020 | $0.00665 |
| Haiku 4.5 | $0.00010 | $0.00332 |
Grade A, and why
data-architect-engineering 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 5d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Architect Engineering
Core Rule
Treat data architecture as a safety-critical engineering system: define workload, data model, access pattern, consistency, security, reliability, operational ownership, and validation before choosing a database, schema, index, shard key, cache, warehouse, or migration path.
First Pass
- Classify the task: database necessity assessment, data model exploration, greenfield design, new datastore creation, data model change, enhancement, migration, legacy modernization, decommissioning, performance tuning, preventive incident review, security review, reliability review, incident troubleshooting, stack selection, DBMS internals review, hardware/storage sizing, monitoring, CDC/data movement, or orchestration.
- Identify workload shape: OLTP, OLAP, HTAP, stream, event log, search, vector retrieval/RAG, graph traversal, document CRUD, time-series ingest/query, key-value/session/cache, queue-like, ML feature store, data lake, data warehouse, or hybrid.
- Ask whether the application needs a database at all, a local embedded database, a file/object store, a cache, an event log, a search/vector index, or a full client/server DBMS.
- Capture non-negotiables: data criticality, RPO/RTO, SLO/SLI, latency percentiles, throughput, data volume/growth, write/read ratio, retention, tenant isolation, compliance, confidentiality, integrity, availability, and recovery evidence.
- Name the data model and query path before naming technology: relational entities, key-value namespaces, graph nodes/edges, document aggregates, column-family partitions, arrays/matrices, hierarchical/network paths, vectors/embeddings, time-series, spatial/geospatial objects, metamodel types, analytical facts/dimensions, lineage, and access patterns.
- Decide validation before recommendation: schema review, ISO SQL/dialect compatibility check, EXPLAIN/plan analysis, storage/page/buffer/WAL evidence, benchmark, load test, migration rehearsal, CDC replay test, restore drill, failover test, consistency check, threat model, data-quality test, or rollback simulation.
What ships with it
45 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.
- agent.md 6.9 KB
- agents/openai.yaml 659 B
- references/cdc-debezium-and-data-movement.md 2.8 KB
- references/data-model-concepts-and-notations.md 10 KB
- references/data-system-intake-and-decision-forces.md 3.6 KB
- references/database-necessity-sqlite-and-scale.md 3.3 KB
- references/database-problem-prevention-and-diagnosis.md 11 KB
- references/database-storage-engine-internals.md 8.2 KB
- references/datastore-taxonomy-and-selection.md 8.4 KB
- references/distributed-dbms-internals.md 4.7 KB
- references/distributed-scaling-newsql-bigdata-warehouse.md 4.3 KB
- references/hardware-acceleration-and-chipset-aware-db.md 3.2 KB
- references/infrastructure-storage-os-and-hardware.md 3.4 KB
- references/migration-profiling-dimensions.md 2.9 KB
- references/modeling-and-query-patterns.md 3.9 KB
- references/nosql-mongodb-performance-tuning.md 15 KB
- references/performance-indexing-and-query-optimization.md 5.3 KB
- references/query-examples-sql-nosql-vector-graph.md 6.4 KB
- references/query-execution-and-optimizer-internals.md 6.2 KB
- references/red-flags.md 2.6 KB
- references/reliability-operations-monitoring.md 3.1 KB
- references/security-governance-and-cia.md 3.5 KB
- references/sql-antipatterns-and-legacy-modernization.md 4.6 KB
- references/sql-standards-and-modern-schema-design.md 3.6 KB
- references/transactions-concurrency-recovery-internals.md 6.1 KB
- scripts/data_architecture_static_audit.py 4.3 KB runs code
- tasks/database-internals-storage-query-recovery-review.md 2.2 KB
- tasks/database-necessity-and-scale-assessment.md 1.4 KB
- tasks/design-new-data-architecture.md 1.9 KB
- tasks/explore-and-decompose-data-model.md 2.1 KB
- tasks/migration-and-modernization.md 1.9 KB
- tasks/modify-enhance-or-remove-data-system.md 1.2 KB
- tasks/performance-troubleshooting.md 2.1 KB
- tasks/prevent-database-performance-incidents.md 1.7 KB
- tasks/security-reliability-review.md 1.3 KB
- tasks/stack-selection-and-next-steps.md 2.2 KB
- templates/capacity-slo-rpo-rto-sheet.md 1.3 KB
- templates/data-model-exploration-matrix.md 2.2 KB
- templates/data-model-review-checklist.md 1.5 KB
- templates/database-problem-risk-register.md 1.5 KB
- templates/datastore-decision-matrix.md 1.1 KB
- templates/dbms-internals-review-checklist.md 1.7 KB
- templates/mermaid-data-architecture-views.mmd 793 B
- templates/mermaid-dbms-internals-views.mmd 1.3 KB
- templates/migration-runbook.md 1.2 KB
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.
- 5d ago First seen · 111 lines · 98 tokens per session scan A 1b1b1db9199b
data-architect-engineering is a skill published in the GitHub repository oghie/skillsets (9 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 3,325 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 2026-08-31.
Other skills, from other repositories
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
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.
debugging
How to debug tursodb using Bytecode comparison, logging, ThreadSanitizer, deterministic simulation, and corruption analysis tools.
sdk-design
Doctrine for designing and evolving any SDK Grida ships — TypeScript, Rust, or otherwise. "SDK" here means a surface that crosses a foreign-or-foreign-treated boundary: published packages, separately-versioned consumers, FFI bindings, public-by-design modules. An SDK's job is to refuse; a strict, honest surface…
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…