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-recursive-fan-out-pattern-rustgit 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-recursive-fan-out-pattern-rust)<a href="https://agentmods.dev/skills/resonatehq/resonate-skills/resonate-recursive-fan-out-pattern-rust"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-recursive-fan-out-pattern-rust/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-recursive-fan-out-pattern-rust"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-recursive-fan-out-pattern-rust.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 | $0.00072 | $0.01683 |
| Opus 5 | $0.00036 | $0.00842 |
| Sonnet 5 | $0.00014 | $0.00337 |
| Haiku 4.5 | $0.00007 | $0.00168 |
Grade A, and why
resonate-recursive-fan-out-pattern-rust 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resonate Recursive Fan-Out Pattern — Rust
SDK note. The Rust SDK is in active development (v0.6.0, on crates.io). This pattern uses
ctx.run().spawn()andctx.rpc().spawn()— both synchronous as of 0.5.0+. Verify against current SDK source before shipping.
Overview
Recursive fan-out spawns multiple child invocations in parallel, awaits them individually, and (optionally) recurses deeper. The Rust expression uses .spawn() on a Context execution builder to get a DurableFuture, collects those futures into a Vec, then awaits each in turn.
For the language-agnostic mental model, see resonate-recursive-fan-out-pattern-typescript.
When to use
- Batch processing where items are independent
- Web crawling / tree traversal with dynamic depth
- Map-reduce shaped workflows
- Any fan-out where each leaf is a discrete, retryable unit
Parallel fan-out in the same process
use resonate::prelude::*;
#[resonate::function]
async fn enrich_batch(ctx: &Context, order_ids: Vec<String>) -> Result<Vec<String>> {
let mut futures = Vec::with_capacity(order_ids.len());
// fire off N children in parallel
for id in order_ids {
let fut = ctx.run(enrich_one, id).spawn()?;
futures.push(fut);
}
// await all; order preserved
let mut results = Vec::with_capacity(futures.len());
for f in futures {
results.push(f.await?);
}
Ok(results)
}
#[resonate::function]
async fn enrich_one(order_id: String) -> Result<String> {
Ok(format!("enriched-{}", order_id))
}
Each enrich_one is a durable promise. If the parent crashes mid-loop, the children are stored server-side; on parent replay, f.await? lookups hit the stored results.
Parallel fan-out across workers
#[resonate::function]
async fn parallel_enrich(ctx: &Context, ids: Vec<String>) -> Result<Vec<String>> {
let mut futures = Vec::with_capacity(ids.len());
for id in ids {
let fut = ctx
.rpc::<String>("enrich_one", id)
.target("poll://any@enrichment-workers")
.spawn()?;
futures.push(fut);
}
let mut results = Vec::with_capacity(futures.len());
for f in futures {
results.push(f.await?);
}
Ok(results)
}
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 · 213 lines · 72 tokens per session scan A e28a1077863f
resonate-recursive-fan-out-pattern-rust is a skill published in the GitHub repository resonatehq/resonate-skills (6 stars, last pushed 20d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,683 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 2026-08-31.
Other skills, from other repositories
golem-make-http-request-rust
Making outgoing HTTP requests from a Rust Golem agent. Use when the user asks to call an external API, make HTTP requests, use an HTTP client, or send HTTP requests from agent code.
golem-add-llm-rust
Adding LLM and AI capabilities to a Rust Golem agent. Use when the user wants to add LLM chat, embeddings, web search, vector DB, graph DB, document search, video generation, speech-to-text, text-to-speech, or any AI provider integration.
golem-parallel-workers-rust
Fan out work to multiple parallel agents and collect results in a Rust Golem project. Use when the user asks about parallel execution, fan-out/fan-in, spawning child agents for parallel work, forking, or aggregating results from multiple agents.
golem-retry-policies-rust
Configuring semantic retry policies for a Rust Golem agent. Use when the user asks about retry policies, retry strategies, exponential backoff, error handling retries, transient error recovery, retry predicates, withRetryPolicy, withnamedpolicy, NamedPolicy, Policy composition, jitter, countBox, timeBox, andThen, or…
golem-add-http-endpoint-rust
Exposing a Rust Golem agent over HTTP. Use when the user asks to add HTTP endpoints, mount an agent to a URL path, or expose agent methods as a REST API.
golem-atomic-block-rust
Using atomic blocks, idempotency, and oplog management in a Rust Golem project. Use when the user asks about atomically, idempotence mode, oplog commit, or idempotency keys.