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 commands/versoxbt/claude-initial-setup/db-reviewgit clone --depth 1 https://github.com/VersoXBT/claude-initial-setupWrote 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/commands/versoxbt/claude-initial-setup/db-review)<a href="https://agentmods.dev/commands/versoxbt/claude-initial-setup/db-review"><img src="https://agentmods.dev/badge/commands/versoxbt/claude-initial-setup/db-review.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 | $0.00008 | $0.00502 |
| Opus 5 | $0.00004 | $0.00251 |
| Sonnet 5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
db-review 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database Review
Audit the database schema, query patterns, and migrations for correctness and performance.
Steps
-
Review the schema:
- Check that tables and columns use consistent naming conventions (snake_case preferred).
- Verify all tables have a primary key.
- Check that foreign keys have proper constraints (ON DELETE, ON UPDATE).
- Verify NOT NULL constraints are applied to required fields.
- Check that default values are set where appropriate.
- Ensure sensitive data columns (passwords, tokens) are not stored in plain text.
-
Check normalization:
- Identify denormalized data that could cause update anomalies.
- Verify no data is duplicated across tables without justification.
- Check that junction tables are used for many-to-many relationships.
- Note any intentional denormalization and confirm it is documented.
-
Review indexes:
- Verify indexes exist on all foreign key columns.
- Check that columns used in WHERE, JOIN, and ORDER BY have appropriate indexes.
- Identify missing indexes on frequently queried columns.
- Check for redundant or duplicate indexes that waste space.
- Verify composite indexes have columns in the correct order.
-
Identify N+1 query patterns:
- Search for loops that execute individual queries inside them.
- Check that related data is loaded with JOINs or eager loading, not lazy loading in loops.
- Verify batch operations are used for bulk inserts and updates.
-
Review query patterns:
- Check for SELECT * usage — only select needed columns.
- Verify pagination is used on list queries (no unbounded result sets).
- Check that complex queries use query builders or named queries, not string concatenation.
- Verify all queries use parameterized inputs (no raw string interpolation).
-
Review migrations:
- Check that migrations are sequential and do not conflict.
- Verify each migration has a corresponding rollback.
- Check that data migrations handle existing data correctly.
- Verify destructive migrations (DROP, ALTER column type) have a safety plan.
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.
- 5d ago First seen · 58 lines · 8 tokens per session scan A c2245b4ac699
db-review is a command published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 3mo ago), licensed MIT. It adds 8 tokens to every session and 502 once invoked, about $0.0000 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.
Other commands, from other repositories
datamodel
Create or modify Prisma-based data models for Nimbalyst's DataModelLM visual editor.
become
Agent crystallization command. Studies a tool, role, or person and produces a portable 9-section agent that inhabits the domain - with beliefs, scar tissue, and instincts.
cycle-start
Activate a cycle and start implementing its stories.
story-continue
Resume an interrupted story from where you left off.
story-archive
Move a story from a cycle back to the backlog.
dial
Live value calibration - 2-4 lettered candidates injected into the running app; click through them against real data, nothing written to source.