Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/resonatehq/resonate-skillsnpx agentmods add skills/resonatehq/resonate-skills/resonate-lovable-usage-prompt-typescriptWrote 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/resonatehq/resonate-skills/resonate-lovable-usage-prompt-typescript)<a href="https://agentmods.dev/skills/resonatehq/resonate-skills/resonate-lovable-usage-prompt-typescript"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-lovable-usage-prompt-typescript/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/resonatehq/resonate-skills/resonate-lovable-usage-prompt-typescript"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-lovable-usage-prompt-typescript.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.06020 |
| Opus 5.5 | $0.00024 | $0.02408 |
| Sonnet 5.5 | $0.00012 | $0.01204 |
| Haiku 4.5 | $0.00006 | $0.00602 |
Grade A, and why
resonate-lovable-usage-prompt-typescript 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 2mo 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 — 873 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resonate Lovable Usage Prompt — TypeScript
SDK version: This skill reflects
@resonatehq/sdkv0.11.4 (current on npm).
Overview
This skill provides specialized guidance for building Resonate durable execution applications within Lovable.dev, an AI-assisted full-stack development environment. Lovable enables rapid prototyping and deployment of React + Node.js applications with built-in hosting.
Core Philosophy: Resonate IS the Database
Critical insight: For workflow state, Resonate is your single source of truth. You don't need a separate database to track workflow status, pending approvals, or execution state.
Traditional approach (unnecessary complexity):
Create workflow → Store in DB → Poll DB for status → Sync with Resonate
Resonate approach (simple):
Create workflow → Query Resonate directly → Done
Why this matters:
- Query promises by ID prefix to list pending items
- Resolve promises to complete workflows
- No DB sync logic, no stale state, no race conditions
When you DO need a database:
- Business data that outlives workflows (user profiles, orders, products)
- Analytics and reporting
- Data that needs relational queries
When you DON'T need a database:
- Workflow status (use Resonate promises)
- Pending approvals (query by prefix)
- Execution state (Resonate tracks this)
Lovable Environment Constraints
What Lovable Provides
- React frontend (Vite + TypeScript)
- Node.js backend (Express + TypeScript)
- PostgreSQL database (Supabase)
- Built-in deployment pipeline
- AI-assisted code generation
- Git integration
Lovable Limitations for Resonate
Lovable does NOT provide:
- Long-running backend processes
- WebSocket servers
- Background workers
- Cron jobs or schedulers
Implication: You cannot run a persistent Resonate worker inside Lovable's backend.
Recommended Architecture for Lovable + Resonate
Architecture A: External Resonate Server (Recommended)
Lovable backend acts as HTTP client to external Resonate:
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.
- 2mo ago First seen · 873 lines · 61 tokens per session scan A 85cb86859f22
resonate-lovable-usage-prompt-typescript is a skill published in the GitHub repository resonatehq/resonate-skills (7 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 6,020 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
golem-js-runtime
JavaScript runtime environment for TypeScript and Scala Golem agents. Use when asking about available APIs, Node.js modules, browser APIs, or runtime capabilities in the QuickJS-based WASM environment.
golem-agent-reflection-ts
Discovering and calling Golem agents through runtime reflection in TypeScript. Use when agent types or methods are selected dynamically, schemas must be inspected at runtime, or only a ParsedAgentId is available.
golem-add-npm-package-effect
Adds npm package dependencies to Effect-based Golem projects. Use when the user asks to add a library, package, or dependency to an @golemcloud/effect-golem application.
golem-add-npm-package
Add a new npm package dependency to a TypeScript Golem project. Use when the user asks to add a library, package, or dependency.
golem-add-sqlite-effect
Use embedded SQLite from an Effect TypeScript Golem agent with the Effect SQL client. Use for local SQL state, SQLite snapshots, or an agent-owned embedded database.
create-workflow-typescript
Creates a TypeScript Dapr app, run locally with dapr run, that demonstrates Workflow, service invocation, pub/sub, bindings, jobs, state and secrets. Use for "create a workflow in TypeScript" or "create a Dapr app in Node.js". For Diagrid Catalyst use the catalyst-ai plugin.