ha-integration-deployer

ha-integration-deployer is an agent for Claude Code from nolte/claude-home-assistant. It costs 214 tokens per session (2,829 once invoked), scanned C, original, MIT.

A deployment agent for placing an already-developed Home Assistant Custom Integration into a running Home Assistant pod in a local Kubernetes cluster. Kubernetes is a system that runs applications in containers, and a pod is one of its running units.

In plain words
What is it for?
Use it to lint an integration, copy it into a Kind cluster’s Home Assistant pod, clear cached bytecode, restart the Home Assistant process, and inspect the result.
Why use it?
It standardizes the checks, file transfer, restart, readiness wait, and log review needed to make the integration available in the running Home Assistant instance.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-home-assistant plugin — 45 skills, 11 agents shipped together

Good fit Use it to lint an integration, copy it into a Kind cluster’s Home Assistant pod, clear cached bytecode, restart the Home Assistant process, and inspect the result.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nolte/claude-home-assistant/ha-integration-deployer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/nolte/claude-home-assistant

Made for: Claude Code.

Or install claude-home-assistant, the plugin that ships this one along with the rest of its 45 skills, 11 agents.

Wrote 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.

agentmods badge for ha-integration-deployer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nolte/claude-home-assistant/ha-integration-deployer/github.svg)](https://agentmods.dev/agents/nolte/claude-home-assistant/ha-integration-deployer)
Your own site
<a href="https://agentmods.dev/agents/nolte/claude-home-assistant/ha-integration-deployer"><img src="https://agentmods.dev/badge/agents/nolte/claude-home-assistant/ha-integration-deployer/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.

agentmods 80×15 button for ha-integration-deployer

Your own site · 80×15
<a href="https://agentmods.dev/agents/nolte/claude-home-assistant/ha-integration-deployer"><img src="https://agentmods.dev/badge/agents/nolte/claude-home-assistant/ha-integration-deployer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 214 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,829 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00214 $0.02829
Opus 5 $0.00107 $0.01414
Sonnet 5 $0.00043 $0.00566
Haiku 4.5 $0.00021 $0.00283

Measured 8d ago against content hash 14582559d84a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

ha-integration-deployer scanned grade C with 1 finding 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 8d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

find <target_dir>/<local_path> -type d -name __pycache__ -exec rm -rf {} +
agents/ha-integration-deployer.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HA Integration Deploy

You are a deployment technician whose only job is to take an already-developed Home Assistant Custom Integration from a local repository and place it into the live HA pod of a local Kubernetes cluster (typically Kind), in a state where the HA process inside the pod recognises the integration on its next start. You never edit the integration under deployment, never restart the cluster, never modify the Helm release, never publish to HACS, and never commit or push.

This agent operationalises the deploy choreography defined in spec/ha/dev-environment/en.md. The single most important rule from that spec, repeated here so you never lose it: kubectl exec <pod> -- kill 1 is the correct restart mechanism. NEVER kubectl delete pod and NEVER kubectl rollout restart. Both destroy the running container, run the init container again, and silently overwrite the files you copied via kubectl cp — your deploy disappears without telling anyone.

Why this is an agent, not a skill

This is an agent rather than a skill because:

  • Multi-stage orchestration with own failure modes — pre-flight lint, pod resolution, local cache cleanup, file copy, remote cache cleanup, restart, wait-on-ready, log tail; each stage has distinct error signatures (lint failure, pod not found, copy failure, kill 1 not in PATH, HA not coming back up, integration setup failure in the log).
  • Latency-bound tool sessionkubectl cp, kubectl exec, and the post-restart wait can take tens of seconds. Running this inline would block the main conversation.
  • Context-window protection — pod logs after a restart can be hundreds of lines (HA boot is verbose); the agent reduces them to a structured PASS / FAIL summary plus the targeted error scan.
  • Narrow tool surface — Bash for kubectl, Read / Glob / Grep on the local repo. No write access to the integration under deployment.
  • Counter-dimension — interactive confirmation ("another integration is broken, want to fix it?") is given up; behaviour is decided up front by the caller's inputs.

Read the full file on GitHub · 211 lines

Changes

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.

  1. 8d ago First seen · 211 lines · 214 tokens per session scan C 14582559d84a

Subscribe to this mod's changes

ha-integration-deployer is an agent published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 214 tokens to every session and 2,829 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

devsecops-engineer

CI/CD security, SAST/DAST pipelines, supply chain security, container scanning, and security automation specialist. Use when securing CI/CD pipelines, implementing security scanning, or hardening build processes. Trigger phrases: DevSecOps, SAST, DAST, supply chain security, container scanning, CI/CD security, SBOM…

travisjneuman/.claude · 83 tokens

devops-engineer

Expert DevOps and cloud infrastructure engineer for AWS, GCP, Azure, Kubernetes, Terraform, and CI/CD pipelines. Use when setting up pipelines, containerizing apps, writing infrastructure as code, or troubleshooting deployments.

travisjneuman/.claude · 48 tokens

cloud-infra-reviewer

Use when you need a read-only review of cloud architecture, infrastructure-as-code, containers, Kubernetes manifests, secrets handling, and deploy topology.

FluxonLab/Skillry · 34 tokens

infrastructure-engineer

Use when you need to author or modify infrastructure-as-code, Dockerfiles, and Kubernetes manifests with hardening and least-privilege defaults.

FluxonLab/Skillry · 33 tokens

planner

An agent that creates plans for complex coding, architecture, or multi-step refactoring work. It interviews the user, examines the codebase, and proposes a short plan with acceptance criteria, without implementing the changes.

sangrokjung/claude-forge · 112 tokens

adversarial-reviewer

Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…

sangrokjung/claude-forge · 102 tokens