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-build-automation)<a href="https://agentmods.dev/skills/gtapps/hermitd/ha-build-automation"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/ha-build-automation/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-build-automation"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/ha-build-automation.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 | $0.00040 | $0.01158 |
| Opus 5.5 | $0.00016 | $0.00463 |
| Sonnet 5.5 | $0.00008 | $0.00232 |
| Haiku 4.5 | $0.00004 | $0.00116 |
Grade A, and why
ha-build-automation 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build HA Automation
Steps
-
Gather context:
- Read
.hermit/raw/snapshot-ha-normalized-latest.jsonfor available entities and services. - Use the stored language from OPERATOR.md (
## HA hermitsection) foraliasanddescriptionfields. - Optionally call
GetLiveContextvia MCP for current state.
- Read
-
Draft the YAML:
- Always include
id:as the first field, using a stable, language-neutral snake_case value (e.g.,kitchen_motion_after_sunset_notification). Thevalidate-applycommand uses this as the REST config ID — omitting it causes a derived, fragile ID that breaks on alias rename. - Use the stored locale for
aliasanddescription. - Set
modeexplicitly where concurrency matters. - Write to
.hermit/raw/automation-<automation_id>.yaml.
- Always include
-
Provision missing helpers:
- Scan the drafted YAML for helper entity IDs (
input_boolean.*,input_number.*,input_text.*,input_select.*,input_datetime.*,timer.*,counter.*,schedule.*) that are absent from the entity inventory snapshot. If none are absent, skip to step 4. - For each distinct helper type among the absent helpers, run
${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha list-helpers --type <type>once to check whether any absent helper of that type already exists under a differententity_id. If found, reference that entity instead. - For each helper that genuinely needs to be created, compose the JSON payload. Minimum required fields by type:
input_boolean/input_text:{"name": "Friendly Name"}input_number:{"name": "...", "min": <N>, "max": <N>}(optional:step,initial,mode)input_select:{"name": "...", "options": ["opt_a", "opt_b"]}input_datetime:{"name": "...", "has_date": true, "has_time": true}timer:{"name": "...", "duration": "HH:MM:SS"}counter:{"name": "...", "initial": 0, "step": 1}schedule:{"name": "..."}with weekday blocks — runha list-helpers --type scheduleto inspect the schema of any existing helper; if none exists, check the HA schedule integration docs for the required block format.
- Preview the helper, then run
${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha create-helper <type> '<json>'and handle the result:"blocked": true;ha_safety_modeisstrict; explain the boundary and create a proposal via/hermitd:proposal-create. Do not retry the denied operation. Continue to validation so the operator sees which entities are still missing."ok": true— helper created; continue.
- If any helpers were created, run
${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha refresh-context --incrementalto update the snapshot before validation.
- Scan the drafted YAML for helper entity IDs (
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.
- 6d ago Changed · +2 lines 0cd30c0a6dcb
- 11d ago First seen · 68 lines · 40 tokens per session scan A 2ff8892368ff
ha-build-automation is a skill published in the GitHub repository gtapps/hermitd (79 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,158 once invoked, about $0.0002 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…
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…
volt-power
Power management audit — analyze sleep modes, wake sources, power state machines, radio duty cycles, and battery life estimates. Use when asked to "audit power usage", "optimize battery life", "review power management", "why is my battery draining", "power budget analysis", or "sleep mode review".
volt-driver
Build a device driver or protocol handler — I2C sensors, BLE services, MQTT clients, SPI peripherals with interrupt-driven I/O and clean HAL abstraction. Use when asked to "write a driver", "I2C device", "BLE service", "MQTT client", or "sensor integration".
volt-recon
Firmware reconnaissance for takeover — inventory the MCU, peripherals, RTOS, protocols, OTA, power management, and assess code quality with risk flags. Use when asked to "understand this firmware", "device inventory", or "embedded assessment".
kicad-jlcpcb-workflow
Use this skill when the user asks to "design a PCB", "make a board", "build a PCB project", "order from JLCPCB", "create a schematic", "source LCSC parts", "wire up a board", "generate a PCB from a BOM", or any KiCad + JLCPCB workflow. Also use when working with .kicadpro or .kicadpcb files. Handles project setup…