data-tier

data-tier is an agent for Claude Code from ivegamsft/basecoat. It costs 36 tokens per session (491 once invoked), scanned A, original, MIT.

A guide for application data storage and access, including schemas, reversible database changes, queries, indexes, caching, backups, and data retention. It focuses on persistent data rather than application features or live operations.

In plain words
What is it for?
Use it to design schemas, write safer migrations, review query performance, plan indexes and caching, and manage retention and backups.
Why use it?
It helps prevent unsafe schema changes, slow queries, missing indexes, and data-access bugs. Reversible migrations and backup planning reduce the risk of losing data during changes.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Codex.

Good fit Use it to design schemas, write safer migrations, review query performance, plan…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-80-data-data-tier
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

Wrote 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.

agentmods badge for data-tier

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-80-data-data-tier.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-80-data-data-tier)
Your own site
<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>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 491 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 37c1a701789f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

agents/basecoat-80-data-data-tier.agent.md · 56 lines

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

  1. Understand domain model — identify entities, attributes, cardinalities, and invariants; clarify soft-delete, audit, and multi-tenancy needs.
  2. Design schema — normalize transactional data to 3NF; document justified denormalization.
  3. Write migrations — every migration needs up and down; require backup and zero-downtime planning for destructive operations.
  4. Implement data access — use repositories, keep queries out of handlers, and parameterize all queries.
  5. Review queries — check for N+1 risk, missing index coverage, unbounded result sets, missing pagination.
  6. 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.
Changes

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.

  1. 3d ago First seen · 56 lines · 36 tokens per session scan A 37c1a701789f

Subscribe to this mod's changes

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.

Related

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.

ASCIT31/Dark-Moon · 56 tokens

data

Use when designing database schemas, writing migrations, optimizing queries, or planning caching strategies.

herbert-julio-azion/specialist-agent · 19 tokens

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…

acaprino/daodan · 91 tokens

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.

DolphinAI2026/dolphin-code · 45 tokens

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…

asiflow/claude-nexus-hyper-agent-team · 313 tokens

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…

nodnarbnitram/claude-code-extensions · 95 tokens