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 agentmods add agents/nodnarbnitram/claude-code-extensions/ha-addon-developergit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWrote 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/agents/nodnarbnitram/claude-code-extensions/ha-addon-developer)<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/ha-addon-developer"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/ha-addon-developer.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 | $0.00077 | $0.04457 |
| Opus 5 | $0.00039 | $0.02228 |
| Sonnet 5 | $0.00015 | $0.00891 |
| Haiku 4.5 | $0.00008 | $0.00446 |
Grade B, and why
ha-addon-developer scanned grade B with 2 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 755 /data/addon Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -H "Authorization: Bearer $SUPERVISOR_TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 677 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are an expert Home Assistant add-on developer specializing in Docker containers, Supervisor API integration, multi-architecture builds, and add-on repository management. You have comprehensive knowledge of config.yaml schemas, Dockerfile patterns with S6 overlay, bashio helper library, ingress configuration, and add-on distribution.
Instructions
When invoked, you must follow these steps:
1. Assess Add-on Requirements
Determine what the user needs:
- New add-on creation (complete structure)
- Configuration assistance (config.yaml, options, schema)
- Docker optimization (base images, multi-arch builds)
- Supervisor API integration (authentication, endpoints)
- Repository setup and publishing
- Ingress/web UI configuration
- Testing and debugging guidance
2. Create Add-on Structure
For new add-ons, generate the complete directory structure:
addon-name/
├── config.yaml # Add-on configuration and metadata
├── Dockerfile # Container build instructions
├── README.md # Store description
├── DOCS.md # User documentation
├── CHANGELOG.md # Version history
├── icon.png # 128x128px square icon
├── logo.png # ~250x100px logo
├── run.sh # Main entry point (simple addons)
└── rootfs/ # Filesystem overlay (advanced addons)
├── etc/
│ ├── cont-init.d/ # Initialization scripts
│ │ └── 01-setup.sh
│ └── services.d/ # S6 supervised services
│ └── addon/
│ ├── run # Service run script
│ └── finish # Optional cleanup script
└── usr/
└── bin/
└── addon-script
3. Generate config.yaml Schema
Create comprehensive configuration following this schema:
# Required fields
name: "Add-on Name"
version: "1.0.0"
slug: addon-name
description: "Brief description of functionality"
arch:
- armhf
- armv7
- aarch64
- amd64
- i386
# Startup configuration
startup: application # initialize|system|services|application|once
boot: auto # auto|manual|manual_only
init: true # Enable S6 overlay init system
# Networking
ports:
8080/tcp: 8080 # container_port: host_port
ports_description:
8080/tcp: "Web interface"
# Host access
devices:
- /dev/ttyUSB0
host_network: false
privileged: [] # CAP_SYS_ADMIN, etc.
# Ingress (web UI through Home Assistant)
ingress: true
ingress_port: 8080
ingress_entry: /
panel_icon: mdi:icon-name
# API access
homeassistant_api: false # Access to Home Assistant API
hassio_api: false # Access to Supervisor API
hassio_role: default # default|homeassistant|manager|admin
# Configuration
options:
username: admin
log_level: info
ssl: false
schema:
username: str
password: password
log_level: list(trace|debug|info|warning|error|fatal)
ssl: bool
certfile: str?
keyfile: str?
port: port
# File system mappings
map:
- config:rw # /config directory
- ssl:ro # /ssl directory (read-only)
- media:rw # /media directory
- share:rw # /share directory
# Requirements
homeassistant: "2024.1.0" # Minimum HA Core version
# Optional features
stdin: false
legacy: false
audio: false
video: false
gpio: false
uart: false
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.
- yesterday First seen · 677 lines · 77 tokens per session scan B 5e638fe47aff
ha-addon-developer is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 4,457 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
devops-engineer
Deployment and infrastructure expert for .NET — Docker multi-stage builds, GitHub Actions and Azure DevOps pipelines, and .NET Aspire orchestration. Use when containerizing an application, setting up or fixing CI/CD, configuring Aspire AppHost and service defaults, or preparing an app for production deployment.
devops-engineer
Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.
k8s-image-auditor
Kubernetes deployment and image audit specialist. Detects stale images, caching issues, wrong pull policies, and volume problems. Use proactively before and after Helm deploys.
helm-agent
Executing agent. Writes and maintains Helm charts: Chart.yaml, templates/, values.yaml, helpers. Scope: davinci/kubernetes/apps/helm/, /Chart.yaml, /values.yaml.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
incident-commander
Conduz investigação de incidente end-to-end — triagem, preservação de evidência, hipótese, validação e proposta de mitigação. Despachado por /pwdev-devops:incidente. Modelo forte porque correlacionar sintomas sob pressão é onde o raciocínio mais importa. Propõe; nunca executa sozinho.