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 skills add resonatehq/resonate-skills --skill resonate-advanced-reasoning-typescriptgit clone --depth 1 https://github.com/resonatehq/resonate-skillsWrote 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-advanced-reasoning-typescript)<a href="https://agentmods.dev/skills/resonatehq/resonate-skills/resonate-advanced-reasoning-typescript"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-advanced-reasoning-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-advanced-reasoning-typescript"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-advanced-reasoning-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 | $0.00065 | $0.01492 |
| Opus 5 | $0.00032 | $0.00746 |
| Sonnet 5 | $0.00013 | $0.00298 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
resonate-advanced-reasoning 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 12d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resonate Advanced Reasoning
Spec Reference
The normative ground truth for promise lifecycle, handler semantics, and state transitions is the Resonate specification — an executable abstract machine in Lean 4:
- Repository: https://github.com/resonatehq/resonate-specification
- Key files:
spec/01-objects/state.lean(promise/task state),spec/02-actions/(P-*.leanfor promise handlers,T-*.leanfor task handlers,S-*.leanfor schedule handlers)
When this skill and the spec diverge, the spec wins.
Overview
Use this skill to translate Resonate specification concepts into Resonate TypeScript SDK usage. Treat the spec as the mental model and the SDK as its concrete expression.
Spec to SDK Translation Map
System Model -> Runtime
- Process -> a single Node.js process running
new Resonate(...). - Logical process -> a group of interchangeable workers (
group+target). - Message passing -> Async RPC over HTTP long poll (or Kafka/SQS transport).
- Addressing ->
poll://any@<group>orpoll://id@<group>targets.
Execution Model -> SDK Semantics
- Execution -> a durable function invocation.
- Invoke event ->
run,rpc,beginRun, orbeginRpc. - Return event -> durable promise resolution stored by the server.
- Durable promise -> the promise ID for each invocation step.
- Resume -> internal callback that replays and continues after a promise resolves.
Programming Model -> SDK APIs
- Durable function ->
resonate.register("name", function* ...). - Local invocation ->
ctx.run/ctx.beginRun. - Remote invocation ->
ctx.rpc/ctx.beginRpcwith target options. - External promise ->
ctx.promise()andresonate.promises.resolve/reject/cancel. - Call graph -> inspect with
resonate tree <id>. - Root promise -> the top-level invocation ID passed to
runorrpc.
Coordination Semantics (Spec -> SDK)
Eventual resumption
Spec: caller awaits a promise that is not yet resolved.
SDK:
- Caller yields
ctx.rpc(...)orctx.beginRpc(...). - Resonate Server stores promise and registers resume callback.
- Caller resumes after the promise is resolved.
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.
- 12d ago First seen · 190 lines · 65 tokens per session scan A 6687e2ff1e65
resonate-advanced-reasoning is a skill published in the GitHub repository resonatehq/resonate-skills (6 stars, last pushed 21d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,492 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
nestjs-expert
Provides NestJS patterns for modules, controllers, providers, guards, interceptors, and microservices. Use when working with NestJS TypeScript files (.module.ts, .controller.ts, .service.ts) or when the user mentions NestJS, Nest.js, or NestJS modules.
adapter-express
Mount tRPC as Express middleware with createExpressMiddleware() from @trpc/server/adapters/express. Access Express req/res in createContext via CreateExpressContextOptions. Mount at a path prefix like app.use('/trpc', ...). Avoid global express.json() conflicting with tRPC body parsing for FormData.
trpc-router
Entry point for all tRPC skills. Decision tree routing by task: initTRPC.create(), t.router(), t.procedure, createTRPCClient, adapters, subscriptions, React Query, Next.js, links, middleware, validators, error handling, caching, FormData.
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
nestjs-expert
Creates and configures NestJS modules, controllers, services, DTOs, guards, and interceptors for enterprise-grade TypeScript backend applications. Use when building NestJS REST APIs or GraphQL services, implementing dependency injection, scaffolding modular architecture, adding JWT/Passport authentication, integrating…
azure-web-pubsub-ts
Build real-time messaging applications using Azure Web PubSub SDKs for JavaScript (@azure/web-pubsub, @azure/web-pubsub-client). Use when implementing WebSocket-based real-time features, pub/sub me...