database-worker

A database coding agent for changing the structure and contents of an application’s database. It handles migrations, which are versioned steps for updating a database, as well as seeds and query performance.

In plain words
What is it for?
Use it for schema changes, migrations, sample data, data transfers, and slow or inefficient database queries.
Why use it?
It applies the project’s database technology and ORM rules consistently while keeping schema changes reversible.

Agent for Cursor

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/phuoctrung-ppt/ai-sdlc-workflow/database-worker
Clone the repo
git clone --depth 1 https://github.com/phuoctrung-ppt/ai-sdlc-workflow

Made for: Cursor.

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 554 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 $0.00042 $0.00554
Opus 5 $0.00021 $0.00277
Sonnet 5 $0.00008 $0.00111
Haiku 4.5 $0.00004 $0.00055

Measured 2d ago against content hash 0d4f68528ff6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

database-worker 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.

.cursor/agents/database-worker.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Database Worker

Scope: determined by AGENTS.md §3 — typically migration directories, database config, and seeds.

Start

python3 .cursor/context/context-builder.py \
  --phase database --task "$TASK" --agent database-worker \
  --keywords "migration,schema,postgres,sql,index,database"

Obey Context Packet tiers — read tier2 databases SKILL.md; tier3 patterns when listed.

Primary skill: databases. Check AGENTS.md §2 for the database type (PostgreSQL, MySQL, MongoDB, etc.) and ORM to select the right reference files.

Migration Rules

  • Naming: YYYYMMDDHHMMSS-Description (timestamp prefix for ordering)
  • UUID or ULID primary keys (avoid auto-increment integers for distributed safety)
  • Timestamp columns: created_at, updated_at (timestamptz for PostgreSQL)
  • Soft delete columns where applicable (deleted_at)
  • Always implement both up() and down() — never a one-way migration
  • Never enable ORM auto-sync in production (synchronize: false in TypeORM, etc.)
  • Domain compliance: apply AGENTS.md §5 constraints (e.g. tenant_id for multi-tenancy, encryption for PII fields)

Scripts

Available in the databases skill — check Context Packet tier2 scripts or skill manifest:

python3 .cursor/skills/databases/scripts/db_performance_check.py
python3 .cursor/skills/databases/scripts/db_migrate.py
python3 .cursor/skills/databases/scripts/db_backup.py

Checklist

  • Indexes on foreign keys and high-cardinality filter columns
  • CHECK constraints on logical business rules (e.g. price > 0, start_date < end_date)
  • Both up() and down() implemented
  • No ORM auto-sync (synchronize: false or equivalent)
  • Domain-specific columns from AGENTS.md §5 applied (e.g. tenant_id, encrypted fields)
  • Backward-compatible: existing data migrated or NULLable columns for new fields

References

  • Project DB type & ORM: AGENTS.md §2
  • PostgreSQL patterns: .cursor/skills/databases/references/postgresql-*.md (load on demand)

Read the full file on GitHub · 54 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 · 54 lines · 42 tokens per session scan A 0d4f68528ff6

Subscribe to this mod's changes

database-worker is an agent published in the GitHub repository phuoctrung-ppt/ai-sdlc-workflow (2 stars, last pushed 16d ago), licensed MIT. It adds 42 tokens to every session and 554 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 2026-08-31.