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 skills/val-town/plugins/sqlite-storagenpx skills add val-town/plugins --skill sqlite-storagegit clone --depth 1 https://github.com/val-town/pluginsWhat 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 | $0.00040 | $0.00666 |
| Opus 5 | $0.00020 | $0.00333 |
| Sonnet 5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
sqlite-storage 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SQLite Storage
Val Town provides built-in SQLite via the std/sqlite module. Reach for it whenever a val needs relational or structured persistent data. For simple key/value data, prefer std/blob instead.
Basic usage
import { sqlite } from "https://esm.town/v/std/sqlite/main.ts";
await sqlite.execute(`CREATE TABLE IF NOT EXISTS users (
id INTEGER PRIMARY KEY,
name TEXT NOT NULL,
email TEXT UNIQUE
)`);
await sqlite.execute({
sql: "INSERT INTO users (name, email) VALUES (?, ?)",
args: ["Alice", "[email protected]"],
});
const result = await sqlite.execute("SELECT * FROM users");
// result.rows = [{ id: 1, name: "Alice", email: "[email protected]" }]
Transactions
Use sqlite.batch for atomic multi-statement transactions — all succeed or all roll back:
await sqlite.batch([
{ sql: "INSERT INTO users (name, email) VALUES (?, ?)", args: ["Bob", "[email protected]"] },
{ sql: "UPDATE users SET name = ? WHERE id = ?", args: ["Robert", 2] },
]);
Per-val vs organization databases
The import path determines which database you get. Both expose the same @libsql/client API (execute, batch) and return rows as keyed objects (Record<string, unknown>[]):
std/sqlite/main.ts— val-scoped database, isolated to this val. The default for new vals, and what you almost always want.std/sqlite/global.ts— organization-scoped database, shared across every val owned by the same account. (Your personal account counts as its own organization here, so this database is shared across all of your vals.)
Do not switch an existing val between these import paths — it changes which database the val reads and writes.
Querying org-owned vals via tools
When using the sqlite_execute or sqlite_batch tools to query a val owned by an organization (not your personal account), pass the org handle as the org parameter so the call hits the right database. Example: { sql: "SELECT * FROM users", org: "some-org" }. This only matters for the tool calls — code inside the val itself reads from its own database automatically.
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.
- 2d ago First seen · 64 lines · 40 tokens per session scan A 6ab49326b577
sqlite-storage is a skill published in the GitHub repository val-town/plugins (10 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 666 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…