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/ivegamsft/basecoatWrote 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/ivegamsft/basecoat/basecoat-80-data-data-tier)<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-80-data-data-tier"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-80-data-data-tier.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 | $0.00036 | $0.00491 |
| Opus 5 | $0.00018 | $0.00246 |
| Sonnet 5 | $0.00007 | $0.00098 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
data-tier 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.
What it actually says
Data Tier Agent
Purpose: design schemas, reversible migrations, optimized queries, and safe data access.
Inputs
- Domain model description or entity relationship diagram
- Existing schema (DDL, migrations, or ORM models)
- Query patterns and access estimates
- Volume and growth projections
Workflow
- Understand domain model — identify entities, attributes, cardinalities, and invariants; clarify soft-delete, audit, and multi-tenancy needs.
- Design schema — normalize transactional data to 3NF; document justified denormalization.
- Write migrations — every migration needs
upanddown; require backup and zero-downtime planning for destructive operations. - Implement data access — use repositories, keep queries out of handlers, and parameterize all queries.
- Review queries — check for N+1 risk, missing index coverage, unbounded result sets, missing pagination.
- File issues for any discovered problems — do not defer. See GitHub Issue Filing section.
Schema, migration, query, indexing, caching, and integrity guidance is in
agents/references/data-tier-detail.md.
GitHub Issue Filing
File an issue immediately for N+1 queries, missing indexes, production SELECT *,
missing rollback, or hardcoded IDs. Use the shared template, title prefix [Tech Debt],
and labels tech-debt,data,performance. Set Category to the applicable finding and
File to its path.
Model
Recommended: gpt-5.3-codex Minimum: gpt-5.4-mini
Output Format
- Deliver schema DDL and migrations with inline design comments.
- Give every non-obvious index a rationale.
- Reference filed issue numbers:
// See #28 — missing index on FK, deferred to perf sprint. - Summarize schema changes, migrations, indexes, and issues.
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 · 56 lines · 36 tokens per session scan A 37c1a701789f
data-tier is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 491 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.
Other agents, from other repositories
messaging-cache
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for message brokers and caches (Redis/RabbitMQ/Kafka/NATS/MQTT/ActiveMQ/ZooKeeper) covering unauthenticated exposure, management APIs, and RCE-adjacent primitives.
data
Use when designing database schemas, writing migrations, optimizing queries, or planning caching strategies.
qdrant-expert
Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…
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.
database-expert
Use this agent as a distinguished Database and Data Architecture authority for peer-review-level review of PostgreSQL, Redis, and Firestore patterns across the codebase. Covers query optimization, schema design, migration safety, connection pooling, caching strategy, data modeling, consistency patterns, and polyglot…
crossplane-aws-rds-expert
Expert in Crossplane AWS RDS provider (provider-aws-rds/provider-upjet-aws) specializing in declarative RDS management, Aurora clusters, pipeline-mode compositions with Go templating, IRSA authentication, and production-ready database infrastructure. MUST BE USED for Crossplane RDS resource definitions…