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 j4flmao/agent-skills --skill serverless-orchestrationgit clone --depth 1 https://github.com/j4flmao/agent-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/j4flmao/agent-skills/serverless-orchestration)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/serverless-orchestration"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/serverless-orchestration/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/j4flmao/agent-skills/serverless-orchestration"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/serverless-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00131 | $0.01821 |
| Opus 5.5 | $0.00052 | $0.00728 |
| Sonnet 5.5 | $0.00026 | $0.00364 |
| Haiku 4.5 | $0.00013 | $0.00182 |
Grade A, and why
cloud-native-serverless-orchestration 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 4d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serverless Orchestration with AWS Step Functions
Purpose
Move workflow state, retries, branching, and compensation out of Lambda code into a declarative state machine. Functions stay small and stateless; Step Functions records every transition, so failures are visible and recoverable.
Agent Protocol
Trigger
"step functions", "state machine", "amazon states language", "ASL", "orchestrate lambdas", "express workflow", "distributed map", "saga", "retry catch workflow".
Input Context
- Steps, their side effects, and which are idempotent.
- Duration and volume (executions/s), need for exactly-once vs at-least-once.
- Human approval or external callbacks.
Output Artifact
ASL definition (JSON) plus IaC wiring. No file unless requested.
Response Format
Workflow type: {Standard|Express (sync|async)} (why)
States: {list}
Error handling: {Retry policies, Catch targets, compensation}
Integrations: {optimized service integrations / Lambda tasks}
Completion Criteria
- Every Task has Retry for transient errors and Catch for terminal ones.
- Workflow type chosen from duration/volume/semantics table.
- Compensating steps defined for any multi-step side effect (saga).
Standard vs Express
| Standard | Express | |
|---|---|---|
| Max duration | 1 year | 5 minutes |
| Execution semantics | Exactly-once per state transition | At-least-once (async) / at-most-once (sync) |
| Pricing | Per state transition | Per request + duration/memory |
| History | Visual execution history, 90 days | CloudWatch Logs only |
Callback (.waitForTaskToken) and .sync job patterns |
Supported | Not supported |
| Fit | Business processes, human approval, long jobs | High-volume event processing, IoT, streaming transforms |
State Types
Task, Choice, Parallel, Map (inline or Distributed mode for up to 10,000 parallel child executions over S3 data), Wait, Pass, Succeed, Fail.
Since late 2024, state machines can set "QueryLanguage": "JSONata" and use Arguments/Output with JSONata expressions instead of JSONPath (InputPath, Parameters, ResultSelector, ResultPath, OutputPath). Pick one per state machine for readability.
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.
- 4d ago Changed · +108 lines · +131 tokens per session 7de87b50bb02
- 1mo ago First seen · 35 lines · 0 tokens per session scan A 300964f32e00
cloud-native-serverless-orchestration is a skill published in the GitHub repository j4flmao/agent-skills (36 stars, last pushed 4d ago), licensed MIT. It adds 131 tokens to every session and 1,821 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
aws-advanced-patterns
Master advanced AWS serverless architectures, event-driven patterns, and enterprise-grade cloud solutions.
serverless-expert
Design and implement production-grade serverless applications with optimal performance, cost efficiency, and scalability. Use when the user mentions serverless or FaaS, AWS Lambda, Azure Functions, Cloud Functions, cold starts, event-driven architecture, or API Gateway-fronted workloads.
serverless-architecture
Designs and implements serverless functions: function boundary design, runtime selection, event sources, IAM least privilege, configuration, observability, and cost estimation. Invoked when the user asks to build a serverless function, design a Lambda-based system, or move workloads to serverless.
serverless
Skill "serverless" from williamzujkowski/standards, covering serverless computing, level 1: quick reference, serverless benefits and tradeoffs, common serverless patterns and essential serverless checklist.
trigger-convex
Integrates Trigger.dev background tasks with Convex using @trigger.dev/convex. Use when triggering work transactionally from a Convex mutation, showing reactive run state, handling completion callbacks, combining Trigger Realtime with Convex, restoring jobs after reload, or repairing paused synchronization. Covers…
workflow
Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of "workflow", "durable functions", "resumable", "workflow sdk", "queue"…