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/tinyplex/tinybase/build-with-tinybasenpx skills add tinyplex/tinybase --skill build-with-tinybasegit clone --depth 1 https://github.com/tinyplex/tinybaseWhat 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 | $0.00076 | $0.00730 |
| Opus 5 | $0.00038 | $0.00365 |
| Sonnet 5 | $0.00015 | $0.00146 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
build-with-tinybase 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build With TinyBase
Prefer a current generated application over reconstructing TinyBase setup from memory. Preserve persistence and synchronization lifecycle ordering, and verify the behavior the user actually needs.
Select The Architecture
Read references/architecture.md when choosing between Store and MergeableStore, persistence backends, synchronization, or UI bindings.
Confirm that TinyBase fits the task:
- Keep the active application dataset in a JavaScript runtime.
- Use TinyBase for reactive tabular or key-value data, local-first behavior, persistence, synchronization, or framework bindings.
- Do not present TinyBase as a hosted database service.
- Pair it with another database or service when the authoritative dataset is unbounded, primarily queried on a server, or requires managed backend facilities.
Scaffold A New Application
Inspect the installed generator contract first:
npm create tinybase@latest -- --list-options
Translate the user's requirements into explicit values. Generate unattended projects with every applicable option and always disable automatic installation and server startup:
npm create tinybase@latest -- \
--non-interactive \
--projectName my-tinybase-app \
--appType todos \
--language typescript \
--framework react \
--tinyWidgets false \
--schemas true \
--syncType none \
--persistenceType local-storage \
--prettier true \
--eslint true \
--installAndRun false
Run the generator in the parent directory that should contain the new project. Do not overwrite an existing directory. After generation:
- Read the generated
AGENTS.mdandREADME.md. - Inspect the primary Store file before modifying application code.
- Install dependencies only when authorized and required.
- Make application-specific changes within the generated architecture.
- Run the generated client build.
- Run the server build when server code changed.
Extend An Existing Application
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 98 lines · 76 tokens per session scan A 66a9cbe2f960
build-with-tinybase is a skill published in the GitHub repository tinyplex/tinybase (5,161 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 730 once invoked, about $0.0004 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
wallet-filter-research
Discover, verify, security-screen, and maintain Solana wallet products using the canonical local registry in packages/ecosystem-data and current web research. Use when asked to refresh wallet data, find new Solana wallets, add or remove wallets, check wallets for scam or security concerns, audit wallet features or…
localize-page
Convert or refactor Solana.com monorepo pages and their directly owned components to the repository's shared i18n system. Use when asked to internationalize, localize, remove hard-coded user-facing copy from, add translations to, or audit a page or route in apps/web, apps/docs, apps/media, apps/templates…
refresh-agent-context
Audit this Turborepo for stale or missing agent-reference docs, then refresh repo and app-level AGENTS.md and related onboarding docs using the bundled workspace inventory script. Use when apps, packages, routes, ports, or shared tooling changed and the repo needs a fresh agent-oriented context pass.
youtube-to-links
Import a YouTube video or full playlist into apps/media/content/links/ as Keystatic MDX entries. Use when the user gives a YouTube URL and asks to add it (or all videos in it) to the media app's links collection. Channel-aware: videos from the Solana Foundation channel (@SolanaFndn) get tagged automatically.
llms-txt-generator
Upgrade llmtxt-generator.py by scanning apps/ for doc structure changes, then regenerate llms.txt and llms-en.txt while only adding missing sections. Use when updating the generator, adding new doc sections, or refreshing LLM text files.
hidden-admin-auth
Configure the private route as a hidden admin utility. Moves credentials to env vars; operator updates .env using .envTemplate instructions. No credentials passed to the skill.