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.
/plugin marketplace add gtapps/hermitd/plugin install hermitd-homeassistantWrote 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/gtapps/hermitd/ha-automation-diff)<a href="https://agentmods.dev/skills/gtapps/hermitd/ha-automation-diff"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/ha-automation-diff/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.
<a href="https://agentmods.dev/skills/gtapps/hermitd/ha-automation-diff"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/ha-automation-diff.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00066 | $0.00505 |
| Opus 5.5 | $0.00026 | $0.00202 |
| Sonnet 5.5 | $0.00013 | $0.00101 |
| Haiku 4.5 | $0.00007 | $0.00051 |
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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ha-automation-diff — 94% identical, 2 lines differ
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
- Run
${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha automation-diff. - The command writes a JSON snapshot to
.hermit/raw/snapshot-ha-automations-latest.json(the baseline for the next run) and a markdown findings artifact under.hermit/raw/audit-ha-automation-diff-*, and prints a stdout findings block. - 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.
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.
- 11d ago First seen · 44 lines · 66 tokens per session scan A 7a0996522900
ha-automation-diff is a skill published in the GitHub repository gtapps/hermitd (79 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 505 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
volt-ota
Produce a complete OTA update system design — partition layout, update flow, rollback conditions, validation checks, fleet management approach, failure modes and recovery. Use when asked about "OTA updates", "firmware updates over the air", "how do I update devices in the field", "OTA strategy", or "remote firmware…
vigil-instrument
Instrument a service with OpenTelemetry — RED metrics, structured logs, distributed tracing, and health checks. Outputs actual code and config, not a plan. Use when asked to "add monitoring", "instrument this", "add logging", "set up tracing", or "observability".
volt-firmware
Produce a complete firmware architecture spec for a described device — layer diagram, module responsibilities, HAL interface definitions, key state machines, RTOS decision. Use when asked to "design firmware architecture", "plan embedded firmware", "architect an IoT device", "how should I structure this firmware", or…
windows-ops
Comprehensive Windows workstation operations - diagnose slow boot, failing drives, BSOD crashes, startup bloat, runaway processes, 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…
touch-audit
Mobile audit — app size, startup time, crash reporting, store compliance, accessibility, offline behavior. Use when asked for "mobile review", "app store readiness", "mobile performance", or "crash analysis".
apex-review
Cross-cutting review of recent work — catches gaps between specialists. Use when asked to "review what we built", "check the work", "pre-launch review", or after completing a significant chunk of work.