Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/skills/masrama/nara/nara-database)<a href="https://agentmods.dev/skills/masrama/nara/nara-database"><img src="https://agentmods.dev/badge/skills/masrama/nara/nara-database.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 | $0.00018 | $0.00848 |
| Opus 5 | $0.00009 | $0.00424 |
| Sonnet 5 | $0.00004 | $0.00170 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
nara-database scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database (SQLite Usage)
Ownership
Feature repositories own SQL. Shared database lifecycle lives in src/shared/database/; route modules and browser code must not access SQLite directly.
import { getDatabase } from '../../../shared/database';
export function findUserById(userId: string): StoredUser | undefined {
return getDatabase()
.prepare(
'SELECT id, name, email, password, avatar, created_at, updated_at FROM users WHERE id = ?',
)
.get(userId) as StoredUser | undefined;
}
Use better-sqlite3 prepared statements for values. Keep row interfaces near the repository that reads them or export them through the Feature's public boundary when another module needs the type.
Parameter binding
Never interpolate user-controlled values into SQL. Bind values through .get(), .all(), or .run():
const pattern = `%${search}%`;
const rows = getDatabase()
.prepare(
`SELECT id, name
FROM products
WHERE name LIKE ?
ORDER BY created_at DESC
LIMIT ? OFFSET ?`,
)
.all(pattern, limit, offset) as ProductRow[];
For dynamic IN clauses, generate one placeholder per validated value and spread the values into the prepared statement:
const placeholders = roleIds.map(() => '?').join(', ');
const rows = getDatabase()
.prepare(`SELECT * FROM roles WHERE id IN (${placeholders})`)
.all(...roleIds) as Role[];
Dynamic identifiers cannot be bound. Prefer fixed SQL; if an identifier must be dynamic, validate it against a closed allowlist before inserting it into the statement.
Transactions
Use a better-sqlite3 transaction for multi-statement writes that must be atomic:
const database = getDatabase();
const replace = database.transaction(() => {
database.prepare('DELETE FROM user_roles WHERE user_id = ?').run(userId);
const statement = database.prepare(
`INSERT INTO user_roles (id, user_id, role_id, created_at)
VALUES (?, ?, ?, ?)`,
);
const now = Date.now();
for (const roleId of roleIds) {
statement.run(randomUUID(), userId, roleId, now);
}
});
replace();
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.
- today First seen · 108 lines · 18 tokens per session scan A 174ab12923af
nara-database is a skill published in the GitHub repository MasRama/nara (5 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 848 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 2026-09-05.
Other skills, from other repositories
architecture-paradigm-space-based
Applies data-grid architecture for high-traffic stateful workloads. Use when a single database cannot scale and in-memory partitioning is needed.
brainctl
Unified agent memory CLI — read, write, search, and maintain the shared memory spine (brain.db). Use for persistent cross-session memory, knowledge graph, event logging, decisions, affect tracking, and consolidation.
database-query
当用户要连接外部数据库(SQLite / MySQL / PostgreSQL)编写 SQL、查询数据、导出结果或分析库表结构时使用。.
Cache Strategy Consistency Guard
Detect undefined or inconsistent cache strategies (layers, consistency, invalidation, TTL, failure handling) in design documents.
event-driven
Event-driven architecture authority — Redis pub/sub, event bus patterns, async event pipelines, channel management, startup recovery, dead-letter handling, and reactive system design.
caching-strategies
When improving read performance and reducing database load.