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-evening-brief)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/ha-evening-brief"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/ha-evening-brief.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 | $0.00038 | $0.01084 |
| Opus 5 | $0.00019 | $0.00542 |
| Sonnet 5 | $0.00008 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
ha-evening-brief 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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA Evening Brief
An end-of-day house check that confirms the house is secure before night. Designed to run as the evening-brief routine at 22:30.
When both claude-code-hermit and claude-code-homeassistant-hermit are installed and evening-brief is enabled, this skill subsumes /claude-code-hermit:brief --evening — operators should disable the core evening routine to avoid duplicate ~22:30 notifications. For hermits without HA, /claude-code-hermit:brief --evening remains the standalone path.
Steps
-
Time & context — Call
GetDateTimefor current time. Read.claude-code-hermit/OPERATOR.mdfor language preferences. -
Live house snapshot — Call
GetLiveContext. Extract and organize:- Security: alarm state, lock states, open covers/blinds
- Devices: robovac status (completed / docked / running / error), lights still on
- Any devices unavailable or in error state
-
Anomalous sensors — From the live snapshot, identify currently unavailable, stuck, or unexpected-state sensors. Report only what is currently wrong — no baseline diff required.
3a. Pending updates: Run ${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha updates --digest and capture stdout. Branch on its content (the command always exits 0 — never branch on exit code):
- Contains
(skipped:— log a single line to SHELL.md## Monitoring(updates fetch failed: <detail after "skipped:">) and omit theUpdates:section entirely. - Contains
(no updates pending)— omit theUpdates:section entirely. - Otherwise — render the digest lines as the
Updates:section, translating tier labels into the operator's language. No proposal-id lookup here (unlike the morning brief).
-
Energy snapshot — From the live context, pull current power draw and day's energy consumption if HA energy entities exist. Omit this section if no energy sensors are available.
-
Compose brief — Write a concise evening brief in the operator's language (from OPERATOR.md). Use the format below.
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.
- 4d ago First seen · 84 lines · 38 tokens per session scan A c0fa0a5df388
ha-evening-brief is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 1,084 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.