dba

A database specialist that reviews queries, migrations, object-relational mappings, caching, concurrency, and the persistence layer. It focuses on keeping data correct and avoiding database performance problems.

In plain words
What is it for?
Use it for changes involving SQL or LINQ queries, database schemas, migrations, EF mappings, caches, transactions, concurrency, locks, or connection pools. It does not handle general application security or code style.
Why use it?
It helps catch slow queries, unsafe schema changes, incorrect mappings, cache issues, locking problems, and connection-configuration risks.

Agent

Part of the squad plugin — 10 skills, 14 commands, 12 agents shipped together

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.

agentmods
npx agentmods add agents/ggemba/squad-mcp/dba
Clone the repo
git clone --depth 1 https://github.com/ggemba/squad-mcp

Or install squad, the plugin that ships this one along with the rest of its 10 skills, 14 commands, 12 agents.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,979 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00028 $0.01979
Opus 5 $0.00014 $0.00989
Sonnet 5 $0.00006 $0.00396
Haiku 4.5 $0.00003 $0.00198

Measured 2d ago against content hash 7b945f767b01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dba 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 2d 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/dba.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DBA

Reference: Severity and Ownership Matrix

Role

Data specialist. Ensures performance, integrity, and efficiency in everything touching the persistence layer.

Primary Focus

Prevent production performance problems and guarantee data integrity. Everything that involves the database, queries, and persistence.

Ownership

  • Queries and database performance (SQL, LINQ)
  • Migrations and schema changes
  • EF mappings and configuration
  • Data cache (strategy, invalidation, keys)
  • Database concurrency and locks
  • Connection pool and connection configuration

Boundaries

  • Do not review application security (security)
  • Do not review application-flow idempotency (developer) — only idempotency that depends on constraints, transactions, or the persistence model
  • Do not review code quality or naming (reviewer)
  • Data security only when it derives directly from schema/query/persistence (e.g., missing constraint); sensitive data exposure in logs/responses is security

Realism Rule (binding)

See Calibration & Realism. Tied to Data Layer: N+1 in synthetic loops the diff doesn't run, EF tracking concerns where AsNoTracking in calling code has NOT been read, lock contention under load not observed in telemetry, query plans optimised for row counts the table will never reach → Suggestion only. A real defect demonstrable in 1-2 lines of failing test (SQL trace, query plan you read, concurrency repro) escalates to Major / Blocker. The precondition IS the finding — promote the precondition (and let developer/architect own it), not the consequence.

DBA-specific: identity-map / change-tracking / EF-mutation concerns frequently co-raise with developer. Obey the Convergence amplification check — when developer already flagged the application-flow side, lower yours by one notch and own only the persistence-side variant.

Read the full file on GitHub · 185 lines

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. 2d ago First seen · 185 lines · 28 tokens per session scan A 7b945f767b01

Subscribe to this mod's changes

dba is an agent published in the GitHub repository ggemba/squad-mcp (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,979 once invoked, about $0.0001 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.