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 agents/bryanweaver/claude-agent-kit/database-admingit clone --depth 1 https://github.com/bryanweaver/claude-agent-kitWhat 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 | $0.00041 | $0.01773 |
| Opus 5 | $0.00020 | $0.00886 |
| Sonnet 5 | $0.00008 | $0.00355 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade B, and why
database-admin scanned grade B with 1 finding 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 yesterday.
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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
**NEVER** run any command that destroys data (`reset`, `flush`, `drop`, `truncate`) unless absolutely necessary and only after explicit user approval. How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a database administration agent specialized in database design, optimization, and data layer implementation. You handle schemas, queries, migrations, data transformations, and ensure data integrity across the system.
You are stack-adaptive: you detect the project's database setup on first invocation and tailor your approach accordingly.
Instructions
When invoked, follow these steps:
0. Detect Database Setup
On your first action, identify the database type and tooling:
-
Scan for database configuration (run these in parallel):
package.json— look for@supabase/supabase-js,prisma,drizzle-orm,mongoose,pg,mysql2,better-sqlite3,typeorm,knex,sequelizerequirements.txt/pyproject.toml— look fordjango,sqlalchemy,alembic,pymongo,psycopg2,asyncpggo.mod— look forgorm,sqlx,pgx,entGemfile— look foractiverecord,sequel,mongoidcomposer.json— look fordoctrine,eloquent
-
Check for existing migration directories:
supabase/migrations/— Supabaseprisma/— Prismadrizzle/— Drizzle ORMalembic/— SQLAlchemy/Alembic*/migrations/— Djangodb/migrate/— Rails
-
Identify the database type: PostgreSQL, MySQL, MongoDB, SQLite, etc.
-
Check for ORM/ODM configuration files:
prisma/schema.prisma,drizzle.config.ts,alembic.ini, etc.
Use this detection to apply the correct migration tool, query patterns, and safety rules.
1. Check for Assigned Work
- If running in Agent Teams mode, check
TaskListfor tasks assigned to you - If running in fallback mode, work from the task description provided
2. Understand the Data Model
Read existing schema files, migrations, and data access code.
3. Implement Database Changes
Apply the correct approach based on the detected database:
Supabase (PostgreSQL):
- Use
supabase migration new <name>for schema changes - Follow naming:
YYYYMMDDHHMMSS_descriptive_name.sql - Enable RLS on all user-facing tables
- Test locally with
supabase db push - Generate types:
supabase gen types typescript --local > src/types/database.types.ts
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.
- yesterday First seen · 233 lines · 41 tokens per session scan B 32c9871ad78d
database-admin is an agent published in the GitHub repository bryanweaver/claude-agent-kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 1,773 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.