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/claude-code-hermit/plugin install claude-code-homeassistant-hermitWrote 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/claude-code-hermit/ha-build-automation)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/ha-build-automation"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/ha-build-automation.svg" alt="Measured on agentmods" 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 | $0.01189 |
| Opus 5 | $0.00020 | $0.00594 |
| Sonnet 5 | $0.00008 | $0.00238 |
| Haiku 4.5 | $0.00004 | $0.00119 |
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 5d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build HA Automation
Steps
-
Gather context:
- Read
.claude-code-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
.claude-code-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.
- Run
${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha create-helper <type> '<json>'and handle the result:"requires_confirm": true—ha_safety_modeisask; describe the helper to the operator and ask for confirmation. On confirm, re-run with--confirm."blocked": true, "requires_confirm": false—ha_safety_modeisstrict; explain the boundary and create a proposal via/claude-code-hermit:proposal-create. Do not retry with--confirm. 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.
- 5d ago First seen · 69 lines · 40 tokens per session scan A 3381d07af78e
ha-build-automation is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,189 once invoked, about $0.0002 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.
Other skills, from other repositories
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. Phase 1.6 handles project…
especialista-em-engenharia-de-hardware
Especialista em Engenharia de Hardware. Use para design eletrônico, microcontroladores, PCB, firmware embarcado, sinais, energia e prototipagem. Palavras-chave: hardware, eletrônica, microcontrolador, PCB, embarcado, firmware, Arduino.
qector-hardware-engineer
Physical-layer quantum circuits, detector-error-model preparation, qLDPC reasoning, and honest target-device hardware reporting for QECTOR. The bundled library MCP server is app-free; the companion bench server adds DEM inspection, DEM collapse, code-family introspection, and hardware probes (all Provisional).…
jensen-skills
Invoke Jensen Huang — Hardware & AI Infrastructure. Use for AI infrastructure planning, GPU and data center strategy, compute TCO analysis, and build-vs-buy decisions. Sets Claude into the Jensen Huang persona for the current conversation.
actual-setup
Set up Actual Computer (actual.inc) inference in Hermes.
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.