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 make-scenario-buildergit 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/make-scenario-builder)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/make-scenario-builder"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/make-scenario-builder/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/make-scenario-builder"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/make-scenario-builder.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 | $0.00082 | $0.01870 |
| Opus 5 | $0.00041 | $0.00935 |
| Sonnet 5 | $0.00016 | $0.00374 |
| Haiku 4.5 | $0.00008 | $0.00187 |
Grade A, and why
make-scenario-builder 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make Scenario Builder
Étape 1 — Cadrage du scénario
Questions à poser avant de toucher l'éditeur :
| Question | Décision |
|---|---|
| Délai acceptable entre événement et action ? | < 1 min → webhook instant ; sinon polling |
| Volume mensuel d'opérations estimé ? | < 10 k → Free ; < 150 k → Core ; au-delà → Pro/Teams |
| Les deux apps sont-elles dans le catalogue Make ? | Oui → module natif ; Non → HTTP / Webhook générique |
| Données à stocker entre exécutions ? | Oui → Data Store ; Non → traitement stateless |
Estimation rapide des opérations :
opérations = nb_exécutions × nb_modules_actifs × taille_collection_moyenne
Exemple : 500 leads/jour × 6 modules × 1 = 3 000 ops/jour → ~90 k/mois (plan Core suffit)
Étape 2 — Trigger
Polling (Watch)
- Intervalle minimum : 1 min (plan payant), 15 min (Free).
- Configurer Max results : commencer à 10, augmenter en production.
- Cocher Process all cycles pour ne pas sauter de lots en cas de retard.
Webhook instant
URL générée : https://hook.eu2.make.com/xxxxxxxxxxxx
Header recommandé : X-Secret-Token: <votre_token>
- Cliquer Redéfinir la structure de données après le premier appel test pour inférer automatiquement le schéma.
- Toujours répondre avec un Webhook Response (200 + corps JSON) sinon l'appelant retente.
{ "status": "ok", "received": true }
Étape 3 — Mapping et transformations
Fonctions utiles copiables dans le panneau de mapping :
# Date ISO → format lisible
{{formatDate(1.created_at; "DD/MM/YYYY HH:mm"; "UTC")}}
# Valeur par défaut si vide
{{ifempty(1.email; "[email protected]")}}
# Extraction de domaine email
{{replace(1.email; "/^.*@/"; "")}}
# Parsing JSON embarqué
{{parseJSON(1.metadata)}}
# Troncature de texte
{{substring(1.description; 0; 255)}}
Règle : mapper à partir des sorties du module précédent (panneau gauche) plutôt que taper en dur — les valeurs hardcodées cassent silencieusement si le schéma source change.
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 · 192 lines · 82 tokens per session scan A bce708836682
make-scenario-builder is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 19d ago), licensed MIT. It adds 82 tokens to every session and 1,870 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
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.
instinct-review
Reviews/promotes/removes instincts from .claude/instincts/.md. Triggers: instinct review, curate instincts, manage instincts, promote instinct.
repeat
Runs prompt/slash command on recurring interval until done or limit. Triggers: repeat, recurring task, poll status, run every N minutes, interval.
night-watch
Autonomous maintenance (dep updates, dead code, small refactors) in isolated branch, off-hours. Triggers: night watch, autonomous maintenance, dep updates.