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 deployment-guidegit 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/deployment-guide)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/deployment-guide"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/deployment-guide/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/deployment-guide"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/deployment-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 42 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
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 | $0.00076 | $0.02381 |
| Opus 5 | $0.00038 | $0.01190 |
| Sonnet 5 | $0.00015 | $0.00476 |
| Haiku 4.5 | $0.00008 | $0.00238 |
Grade A, and why
deployment-guide 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 11d 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Deployment Guide
Quand utiliser ce skill
Passage d'un agent fonctionnel en local vers un déploiement production fiable et scalable. Couvre API synchrone, worker asynchrone, webhook, tâche planifiée, streaming temps réel. Applicable sur AWS, Azure, GCP, ou infrastructure on-premise.
Étape 1 — Choisir le pattern de déploiement
| Pattern | Quand l'utiliser | Latence max | Exemple |
|---|---|---|---|
| API synchrone (FastAPI) | Usage interactif, réponse < 30s | 29s | Chatbot, Q&A |
| Worker async (Celery/Bull) | Tâches longues, batch | Illimité | Analyse de docs, rapport |
| Webhook handler | Événements externes (GitHub, Slack) | 3s (ACK) | Bot Slack, CI/CD agent |
| Scheduled agent (cron) | Récurrent, pas de déclencheur externe | N/A | Rapport hebdo, cleanup |
| Streaming SSE/WebSocket | UX conversationnelle temps réel | < 1s TTFB | Assistant interactif |
Critère décisif : si la réponse prend > 30s → worker async + polling/webhook. Sinon → API synchrone.
Étape 2 — Containeriser l'agent
# Dockerfile multi-stage (léger et sécurisé)
FROM python:3.12-slim AS builder
WORKDIR /build
COPY requirements.txt .
RUN pip install --no-cache-dir --prefix=/install -r requirements.txt
FROM python:3.12-slim
WORKDIR /app
COPY --from=builder /install /usr/local
COPY . .
# Pas de root en prod
RUN useradd -m appuser && chown -R appuser /app
USER appuser
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8080", "--workers", "4"]
Points critiques :
- Tag Docker immutable (
image:v1.2.3), jamaislatesten prod - Secrets → volume/secret manager, jamais
COPY .envdans l'image - Model weights → volume monté ou téléchargement S3 au démarrage, pas dans l'image
Étape 3 — Wrapper API robuste
# main.py — FastAPI avec health checks et streaming
from fastapi import FastAPI, HTTPException
from fastapi.responses import StreamingResponse
from pydantic import BaseModel, Field
import asyncio, uuid, os
app = FastAPI()
class AgentRequest(BaseModel):
message: str = Field(..., max_length=4000)
conversation_id: str = Field(default_factory=lambda: str(uuid.uuid4()))
@app.get("/health") # liveness probe
async def health(): return {"status": "ok"}
@app.get("/ready") # readiness probe
async def ready():
# Vérifier dépendances critiques
try:
await check_llm_api() # ping minimal
await check_redis()
except Exception as e:
raise HTTPException(503, detail=str(e))
return {"status": "ready"}
@app.post("/run")
async def run_agent(req: AgentRequest):
async def stream():
async for chunk in agent.run_stream(req.message, req.conversation_id):
yield f"data: {chunk}\n\n"
return StreamingResponse(stream(), media_type="text/event-stream")
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.
- 11d ago First seen · 287 lines · 76 tokens per session scan A 06af0afb1db6
deployment-guide is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 17d ago), licensed MIT. It adds 76 tokens to every session and 2,381 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 2026-08-30.
Other skills, from other repositories
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.
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.
java-patterns
Java: Spring Boot, CompletableFuture, records, sealed types, JPA/Hibernate, virtual threads. Triggers: Java, Spring, JPA, Hibernate, Maven, Gradle, virtual thread, sealed class.
explain
Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.
common-sense-index-investing-bogle
Apply John Bogle index investing rules for low-cost funds, asset allocation, fees, taxes, ETFs, advisers, and buy-hold discipline.
medplum-rules
Medplum (FHIR healthcare) coding rules: style, patterns, security, testing. Triggers: medplum.config.mts, medplum.config.ts, FHIR, Medplum, Bot, Subscription, Questionnaire.