ha-dual-smart-thermostat: Command for Claude Code

.claude/commands/release.md

release is a command for Claude Code from swingerman/ha-dual-smart-thermostat. It costs 29 tokens per session (1,138 once invoked), scanned A, original, Apache-2.0.

A command that prepares and publishes a stable software release. A stable release is a version intended for normal users rather than testing.

In plain words
What is it for?
Use it to check the version, compare changes since the last stable release, update the manifest when needed, create release notes, and publish the release.
Why use it?
It reduces the chance of missing changes, using the wrong version, or publishing incomplete release notes.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is swingerman/ha-dual-smart-thermostat's own configuration. It tells Claude Code how to work on ha-dual-smart-thermostat itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ha-dual-smart-thermostat configures →

Reuse

Borrowing it

Nothing to install: this file belongs to swingerman/ha-dual-smart-thermostat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/swingerman/ha-dual-smart-thermostat/master/.claude/commands/release.md
Clone the repo
git clone --depth 1 https://github.com/swingerman/ha-dual-smart-thermostat

Made for: Claude Code.

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 release

README.md
[![agentmods](https://agentmods.dev/badge/commands/swingerman/ha-dual-smart-thermostat/release/github.svg)](https://agentmods.dev/commands/swingerman/ha-dual-smart-thermostat/release)
Your own site
<a href="https://agentmods.dev/commands/swingerman/ha-dual-smart-thermostat/release"><img src="https://agentmods.dev/badge/commands/swingerman/ha-dual-smart-thermostat/release/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 release

Your own site · 80×15
<a href="https://agentmods.dev/commands/swingerman/ha-dual-smart-thermostat/release"><img src="https://agentmods.dev/badge/commands/swingerman/ha-dual-smart-thermostat/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,138 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00029 $0.01138
Opus 5 $0.00015 $0.00569
Sonnet 5 $0.00006 $0.00228
Haiku 4.5 $0.00003 $0.00114

Measured 9d ago against content hash cc58b3d3fd6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release 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.

.claude/commands/release.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Release

Create a stable release for Dual Smart Thermostat.

User Input

$ARGUMENTS

Consider the user input above (if provided) for the release title or extra context.

Workflow

Follow these steps in order:

1. Determine Version and Gather Changes

  • Read the current version from custom_components/dual_smart_thermostat/manifest.json
  • Find the last stable (non-prerelease) release: gh release list --limit 20 and filter out pre-releases
  • Verify the manifest version is higher than the last stable release; if not, ask the user
  • Gather ALL commits since the last stable release:
    git log <last-stable-tag>..HEAD --oneline
    
  • Also check beta release notes for this version to ensure nothing is missed

2. Verify Manifest

  • Confirm manifest.json version matches the intended release version (without "beta")
  • If it already matches (from a prior beta bump), no change needed
  • If it needs updating, edit, commit (chore: bump version to vX.Y.Z), and push

3. Generate Release Notes

Write release notes following this exact format and tone:

## 🎉 What's New in vX.Y.Z

One or two enthusiastic sentences summarizing the headline value of this release. Focus on what users gain — comfort, reliability, new capabilities. Be specific.

---

## ✨ New Features

### 🌀 Feature Title
**One bold sentence explaining the user-facing value.**

- Bullet points with details the user cares about
- Focus on what changed for THEM, not implementation details
- Include before/after if helpful

- Details: #issue1, #issue2

---

## 🐛 Bug Fixes

### 🔧 Fix Title (user-facing description)
Description of what was broken and how it affected users. Be enthusiastic that it's fixed — these matter to people!

**Example:** If applicable, show a concrete before/after scenario.

- Details: #issue1, #issue2

---

## 📊 By the Numbers

- **N new features** — brief labels
- **N bug fixes** — brief labels
- **N tests** — all passing
- **100% backward compatible** — no configuration changes needed (or note if there ARE changes)

---

## 🔄 Migration Guide

**Drop-in replacement.** No configuration changes required.

Or, if there ARE migration steps, list them clearly with examples.

---

## 💝 Support This Project

If this integration makes your home smarter and more comfortable, consider supporting development:

[![Donate](https://img.shields.io/badge/Donate-PayPal-yellowgreen?style=for-the-badge&logo=paypal)](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=S6NC9BYVDDJMA&source=url)
[![coffee](https://www.buymeacoffee.com/assets/img/custom_images/black_img.png)](https://www.buymeacoffee.com/swingerman)

Your support helps maintain this integration and develop new features! ☕️

---

**Full Changelog**: https://github.com/swingerman/ha-dual-smart-thermostat/compare/<last-stable-tag>...vX.Y.Z

---

💙 **Enjoying this integration?** Help others discover it:
- ⭐ Star the repository
- 🐛 Report issues you encounter
- 💬 Share your success stories
- 📣 Recommend to the Home Assistant community

Read the full file on GitHub · 143 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. 9d ago First seen · 143 lines · 29 tokens per session scan A cc58b3d3fd6d

Subscribe to this mod's changes

release is a command published in the GitHub repository swingerman/ha-dual-smart-thermostat (233 stars, last pushed 8d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,138 once invoked, about $0.0001 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.