Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pjt222/agent-almanacnpx agentmods add skills/pjt222/agent-almanac/deploy-shinyproxyWrote 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/pjt222/agent-almanac/deploy-shinyproxy)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/deploy-shinyproxy"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/deploy-shinyproxy.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.02391 |
| Opus 5 | $0.00045 | $0.01196 |
| Sonnet 5 | $0.00018 | $0.00478 |
| Haiku 4.5 | $0.00009 | $0.00239 |
Grade D, and why
deploy-shinyproxy scanned grade D with 3 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -c cookies.txt -d "username=admin&password=admin_password" \ Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
&& rm -rf /var/lib/apt/lists/* Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:8080/actuator/health How it starts
The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy ShinyProxy
Deploy ShinyProxy to host multiple containerized Shiny applications with authentication and usage tracking.
When to Use
- Hosting multiple Shiny apps behind a single entry point
- Need per-app authentication and access control
- Deploying Shiny apps as isolated Docker containers
- Scaling beyond single-app deployment (shinyapps.io or standalone Docker)
- Requiring usage analytics and audit logging
Inputs
- Required: One or more Shiny apps to deploy
- Required: Server with Docker installed
- Optional: Authentication provider (LDAP, OpenID, social)
- Optional: Domain name and SSL certificate
- Optional: Container orchestrator (Docker or Kubernetes)
Procedure
Step 1: Create Shiny App Docker Images
Each Shiny app needs its own Docker image. Example Dockerfile for a Shiny app:
FROM rocker/shiny:4.5.0
RUN apt-get update && apt-get install -y \
libcurl4-openssl-dev \
libssl-dev \
&& rm -rf /var/lib/apt/lists/*
RUN R -e "install.packages(c('shiny', 'bslib', 'DT', 'dplyr'), \
repos='https://cloud.r-project.org/')"
COPY app/ /srv/shiny-server/app/
RUN chown -R shiny:shiny /srv/shiny-server/app
USER shiny
EXPOSE 3838
CMD ["R", "-e", "shiny::runApp('/srv/shiny-server/app', host='0.0.0.0', port=3838)"]
Build and test each app:
docker build -t myorg/dashboard:latest ./apps/dashboard/
docker run --rm -p 3838:3838 myorg/dashboard:latest
Got: Each Shiny app runs independently in its own container.
Step 2: Configure ShinyProxy
application.yml:
proxy:
title: "Shiny Applications"
port: 8080
container-backend: docker
docker:
internal-networking: true
authentication: simple
admin-groups: admins
users:
- name: admin
password: admin_password
groups: admins
- name: analyst
password: analyst_password
groups: users
specs:
- id: dashboard
display-name: "Analytics Dashboard"
description: "Interactive data analysis dashboard"
container-image: myorg/dashboard:latest
container-cmd: ["R", "-e", "shiny::runApp('/srv/shiny-server/app', host='0.0.0.0', port=3838)"]
container-network: shinyproxy-net
port: 3838
access-groups: [admins, users]
- id: report-builder
display-name: "Report Builder"
description: "Generate custom reports"
container-image: myorg/report-builder:latest
container-cmd: ["R", "-e", "shiny::runApp('/srv/shiny-server/app', host='0.0.0.0', port=3838)"]
container-network: shinyproxy-net
port: 3838
access-groups: [admins]
logging:
file:
name: /opt/shinyproxy/log/shinyproxy.log
server:
forward-headers-strategy: native
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 First seen · 328 lines · 90 tokens per session scan D bc2e4ba1cc0a
deploy-shinyproxy is a skill published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 2,391 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
wrangler
Run or troubleshoot Wrangler CLI commands and configure Worker projects for local development, deployment, and Cloudflare resource management.
aws-cloudformation-ecs
Provides AWS CloudFormation patterns for ECS clusters, task definitions, services, container definitions, auto scaling, blue/green deployments, CodeDeploy integration, ALB integration, service discovery, monitoring, logging, template structure, parameters, outputs, and cross-stack references. Use when creating ECS…
loom-kubernetes
Kubernetes deployment, cluster architecture, security, and operations.
loom-karpenter
Kubernetes node autoscaling and cost optimization with Karpenter.
northflank
Deploy, manage, and automate infrastructure on Northflank — a developer platform for building, deploying, and scaling services, jobs, databases, and release workflows on Kubernetes. Use when managing Northflank projects, services, jobs, addons (databases), secrets, domains, templates (IaC), environments, preview…
kubernetes
WHAT: Kubernetes manifest generation - Deployments, StatefulSets, CronJobs, Services, Ingresses, ConfigMaps, Secrets, and PVCs with production-grade security and health checks. WHEN: User needs to create K8s manifests, deploy containers, configure Services/Ingress, manage ConfigMaps/Secrets, set up persistent storage…