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 khalilbenaz/claude-skills-collection --skill serverless-designergit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/serverless-designer)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/serverless-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/serverless-designer/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/khalilbenaz/claude-skills-collection/serverless-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/serverless-designer.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 | $0.00081 | $0.02030 |
| Opus 5 | $0.00041 | $0.01015 |
| Sonnet 5 | $0.00016 | $0.00406 |
| Haiku 4.5 | $0.00008 | $0.00203 |
Grade A, and why
serverless-designer 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 9d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serverless Designer
Workflow
1. Évaluer l'adéquation serverless
Appliquer la grille de décision avant tout design :
| Critère | Serverless ✅ | Conteneur/VM ❌ |
|---|---|---|
| Durée d'exécution | < 15 min (Lambda), < 10 min (AZ Func) | Longue durée / streaming |
| Trafic | Très variable, spiky | Stable et prévisible |
| Cold start toléré | Oui (< 2 s acceptable) | Non (latence < 50 ms requise) |
| État local requis | Non | Oui (session, cache local) |
| Charge réseau | Faible à modérée | Très haute (> 10 K req/s en continu) |
Si 3 critères ou plus sont dans la colonne droite, proposer un déploiement conteneurisé (ECS/AKS/Cloud Run).
2. Cartographier les déclencheurs
Lister tous les événements et associer chaque source à une fonction :
HTTP/REST → API Gateway + Lambda / Azure APIM + Function
File upload → S3 Event / Blob Trigger
Message queue → SQS / Service Bus → fonction consumer
Timer/CRON → EventBridge Scheduler / Timer Trigger
Stream → Kinesis / Event Hub → fonction par batch
Auth event → Cognito / AAD B2C → Pre/Post trigger
Documenter le schéma de l'événement d'entrée dès cette étape pour éviter les surprises au déploiement.
3. Découper les fonctions (SRP)
- 1 fonction = 1 responsabilité = 1 déclencheur
- Timeout explicite (ne jamais laisser le défaut)
- Taille de payload max définie (ex. 6 MB Lambda, 100 MB AZ Functions)
- Extraire la logique métier dans des modules testables indépendamment du handler
# Handler thin — délègue à un module testable
def handler(event, context):
payload = parse_event(event) # module pur
result = process_order(payload) # logique métier
return format_response(result) # module pur
4. Choisir plateforme et runtime
Comparatif 2026 rapide :
| Plateforme | Runtime top | Timeout max | Cold start typique |
|---|---|---|---|
| AWS Lambda | Python 3.12, Node 22, Java 21 | 15 min | 200 ms–1 s (SnapStart Java) |
| Azure Functions v4 | .NET 8 Isolated, Node 20 | 10 min (Consumption) | 300 ms–2 s |
| Google Cloud Functions 2nd gen | Python 3.12, Go 1.22 | 60 min | 100–500 ms |
| Cloudflare Workers | JS/TS (V8 Isolates) | 30 s CPU | < 5 ms (pas de cold start) |
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.
- 9d ago First seen · 195 lines · 81 tokens per session scan A 47d48eb1ffdc
serverless-designer is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 19d ago), licensed MIT. It adds 81 tokens to every session and 2,030 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 2026-09-03.
Other skills, from other repositories
n8n-workflow
Build n8n automation workflows — nodes, expressions, error handling, and self-hosted deployment.
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
api-patterns
API design: naming, versioning, pagination, idempotency, OpenAPI, error contracts and safe retries. Triggers: API design, REST, GraphQL, OpenAPI, Swagger, error response, HTTP status, rate limit.
csharp-patterns
C#/.NET: LINQ, async/await, DI, records, nullable refs, ASP.NET Core, EF Core, MediatR. Triggers: C#, .NET, dotnet, ASP.NET, EF Core, LINQ, record type, IServiceCollection.
java-patterns
Java: Spring Boot, CompletableFuture, records, sealed types, JPA/Hibernate, virtual threads. Triggers: Java, Spring, JPA, Hibernate, Maven, Gradle, virtual thread, sealed class.
rollback
Rolls back git commit, DB migration, or deploy to known-good with safety + health checks. Triggers: rollback, revert deploy, revert migration, rollback commit, git revert.