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/nxtg-ai/forge-plugin/databasegit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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 | $0.00000 | $0.01880 |
| Opus 5 | $0.00000 | $0.00940 |
| Sonnet 5 | $0.00000 | $0.00376 |
| Haiku 4.5 | $0.00000 | $0.00188 |
Grade A, and why
database 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 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.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database
Designs schemas that enforce business rules, creates safe reversible migrations, and optimizes queries -- because your data layer is your application's foundation.
| Level | L1 Vibe Coder |
| Category | Domain Specialist |
| Model | Sonnet |
What It Does
The Database agent is the specialist for everything below the API layer: schema design, data modeling, migration creation, query optimization, and storage strategy. It knows that schema design is not just about tables and columns -- it is about encoding business rules into constraints, choosing normalization levels that balance integrity against performance, and designing indexes that make the queries you actually run fast.
In the NXTG-Forge ecosystem, data persistence uses JSON files (.claude/state/), in-memory stores (runtime data like activities and sessions), and localStorage (client-side state). The Database agent understands this landscape and recommends the right storage for each use case -- SQLite for structured relational data that needs querying, JSON files for configuration and governance state, in-memory stores for ephemeral session data. When the project grows beyond file-based storage, it designs proper migration strategies with up and down paths.
What makes this agent more than a schema generator is its understanding of data integrity. Every schema it designs includes Zod validation schemas for runtime type checking, foreign key relationships for referential integrity, and index strategies for the access patterns the application actually uses. It treats migrations as code -- version controlled, reviewed, tested, and never modified after creation. When queries are slow, it does not just add indexes blindly; it analyzes the actual access patterns and designs an indexing strategy that scales.
When to Use It
- Adding a new data model: When your feature needs persistent storage and you need schema design, Zod validation schemas, and migration scripts.
- Optimizing slow queries: When a database operation takes too long and you need query analysis, index recommendations, and caching strategy.
- Designing data relationships: When you need to model complex relationships (one-to-many, many-to-many, versioned data) with proper constraints and efficient access patterns.
- Migrating storage strategies: When you are moving from JSON files to SQLite, or from in-memory to persistent storage, and need a safe migration path.
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 · 137 lines · 0 tokens per session scan A 792d4de1d937
database is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,880 tokens. 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 agents, from other repositories
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
emulate-engineer
Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.
TESTING
This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.