ha-automation-diff

ha-automation-diff is a skill for Claude Code from gtapps/claude-code-hermit. It costs 66 tokens per session (511 once invoked), scanned A, original, MIT.

A read-only change report for Home Assistant automations. It compares the current automation configurations with an earlier snapshot, including changes made directly in the Home Assistant interface.

In plain words
What is it for?
Use it to find automations that were added, removed, edited, enabled, or disabled since the previous snapshot.
Why use it?
It shows what changed between sessions, which can help explain a broken or altered automation without relying on memory.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-code-homeassistant-hermit plugin — 18 skills, 3 agents shipped together

Good fit Use it to find automations that were added, removed, edited, enabled, or disabled since the previous snapshot.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add gtapps/claude-code-hermit
Claude Code
/plugin install claude-code-homeassistant-hermit

Made for: Claude Code.

Or install claude-code-homeassistant-hermit, the plugin that ships this one along with the rest of its 18 skills, 3 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-automation-diff

README.md
[![agentmods](https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/ha-automation-diff.svg)](https://agentmods.dev/skills/gtapps/claude-code-hermit/ha-automation-diff)
Your own site
<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/ha-automation-diff"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/ha-automation-diff.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 511 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 $0.00066 $0.00511
Opus 5 $0.00033 $0.00255
Sonnet 5 $0.00013 $0.00102
Haiku 4.5 $0.00007 $0.00051

Measured 3d ago against content hash c59c4b924817, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ha-automation-diff 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 3d 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.

plugins/claude-code-homeassistant-hermit/skills/ha-automation-diff/SKILL.md · 44 lines

What it actually says

HA Automation Diff

Purpose

ha-safety-audit catches POLICY drift at a point in time. This skill catches CHANGE drift: which automations were added, removed, edited, enabled, or disabled since the last snapshot — including edits made directly in the HA UI that bypass ha-build-automation. It gives the hermit a memory of "what moved" between sessions, which is what explains regressions and keeps the estate legible.

It is read-only against Home Assistant: it enumerates automations, hashes each stored config, and diffs against the previous snapshot.

Steps

  1. Run ${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha automation-diff.
  2. The command writes a JSON snapshot to .claude-code-hermit/raw/snapshot-ha-automations-latest.json (the baseline for the next run) and a markdown findings artifact under .claude-code-hermit/raw/audit-ha-automation-diff-*, and prints a stdout findings block.
  3. Pass the stdout block through unchanged.

Output contract

ha-automation-diff findings — YYYY-MM-DD
Changes since last snapshot: K
- added: <name> (`<id>`)
- removed: <name> (`<id>`)
- edited: <name> (`<id>`)
- disabled: <name> (`<id>`)
- enabled: <name> (`<id>`)
Untracked (YAML-packaged, config not diffable): M

First run (no prior snapshot): Baseline established. (N automations tracked).

No changes: No changes since last snapshot. (N automations tracked).

Failure modes

  • HA unreachable → CLI exits non-zero with an error message. Treat as "skipped, cannot diff"; do not retry automatically.
  • YAML-packaged automations have no numeric id and are not REST-retrievable, so their config is not diffable. They are counted under "Untracked" rather than silently dropped — the diff is honest about what it does not cover.
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. 3d ago First seen · 44 lines · 66 tokens per session scan A c59c4b924817

Subscribe to this mod's changes

ha-automation-diff is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 511 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

windows-ops

Comprehensive Windows workstation operations - diagnose slow boot, failing drives, BSOD crashes, startup bloat, event logs. Use for: Windows is slow, slow bootup, won't boot, blue screen, BSOD, kernel crash, drive failing, SMART errors, disk errors, Event 41, Event 129, storahci reset, BugCheck, CRITICALPROCESSDIED…

0xDarkMatter/claude-mods · 176 tokens

tia-doctor

Manual, read-only prerequisite probe for TIA Portal V21 and its modular Openness API, with optional Python TIA Scripting and TIA MCP checks.

Czarnak/totally-integrated-claude · 36 tokens

diagnose-hid-keycodes

Find out what an unknown USB/Bluetooth HID button actually emits without assuming the label or documentation. Uses Karabiner's.

terrylica/cc-skills · 32 tokens

issue-debugging

Systematic methodology for issue debugging including root cause analysis, impact mapping, tiered validation plans, and confidence assessment. Use when analyzing bugs, fixing issues, or validating fixes.

QBall-Inc/the-bulwark · 39 tokens

fix-bug

Run the Fix Validation pipeline to investigate, fix, and validate a bug. Ensures deterministic pipeline execution with IssueAnalyzer, FixWriter, TestWriter (conditional), TestAudit (conditional), and FixValidator stages.

QBall-Inc/the-bulwark · 46 tokens

ccc-systematic-debugging

Root-cause debugging via the Iron Law: no fix without confirmed root cause. Reproduce → hypothesize → verify → fix. Use when investigating bugs, test failures, or…

KevinZai/commander · 42 tokens