ha-refresh-context

ha-refresh-context is a skill for Claude Code from gtapps/claude-code-hermit. It costs 27 tokens per session (506 once invoked), scanned A, original, MIT.

A context-refresh tool for Home Assistant that fetches the current state of the home and saves a normalized record of its entities, devices, areas, and services.

In plain words
What is it for?
It helps prepare accurate context before creating automations and records changes to the home's setup.
Why use it?
It prevents automations from being designed using outdated or incomplete information about the home.

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 It helps prepare accurate context before creating automations and records changes to the home's setup.

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-refresh-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/ha-refresh-context.svg)](https://agentmods.dev/skills/gtapps/claude-code-hermit/ha-refresh-context)
Your own site
<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/ha-refresh-context"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/ha-refresh-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 506 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 $0.00027 $0.00506
Opus 5 $0.00014 $0.00253
Sonnet 5 $0.00005 $0.00101
Haiku 4.5 $0.00003 $0.00051

Measured 4d ago against content hash eb9645805000, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ha-refresh-context 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.

plugins/claude-code-homeassistant-hermit/skills/ha-refresh-context/SKILL.md · 36 lines

What it actually says

HA Refresh Context

Steps

  1. Run ${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha refresh-context.
  2. Read the output JSON — note entity count and base_url_source.
  3. Read .claude-code-hermit/raw/snapshot-ha-normalized-latest.json to understand what's in the house.
  4. Compare with the previous entity count (check your auto memory for a stored house profile).
  5. If new entities, areas, or domains appeared, update your auto memory with the house profile changes.
  6. If entities disappeared or became unavailable, note it in your auto memory.

Output

  • .claude-code-hermit/raw/snapshot-ha-context-<date>.json + snapshot-ha-context-latest.json — raw HA API snapshot
  • .claude-code-hermit/raw/snapshot-ha-normalized-latest.json — processed entity/service index (fixed name)
  • .claude-code-hermit/raw/audit-ha-context-refresh-<date>.md + audit-ha-context-refresh-latest.md — audit entry

House profile (first run or when profile changes): if new areas, domains, or significant entity changes are observed in step 5, write a durable house profile summary to .claude-code-hermit/compiled/context-house-profile-<YYYY-MM-DD>.md with frontmatter type: context, title: "House Profile — <date>", created: <ISO8601>, session: <session_id or null>, tags: [ha-context, house-profile, foundational], injection_stub: "House profile: <N> areas, <M> entities, <K> automations. Read compiled/context-house-profile-<date>.md for detail." (fill in the real counts). Append [[compiled/context-house-profile-<date>]] to SHELL.md ### Artifacts produced this session under ## Monitoring.

When to Use

  • Session start (via ha-boot) when context is stale
  • Before building any automation
  • After the operator reports changes to their HA setup
  • Periodically to detect drift
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. 4d ago First seen · 36 lines · 27 tokens per session scan A eb9645805000

Subscribe to this mod's changes

ha-refresh-context is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 506 once invoked, about $0.0001 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

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…

BeckhamLabsLLC/kicad-jlcpcb · 145 tokens

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.

euwebertdefreitas/ai-skills-for-claude-code · 63 tokens

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).…

GuillaumeLessard/qector-claude-plugin · 103 tokens

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.

markusbegerow/board-of-directors · 50 tokens

actual-setup

Set up Actual Computer (actual.inc) inference in Hermes.

NousResearch/hermes-agent · 16 tokens

cco-tools

Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.

egorfedorov/claude-context-optimizer · 27 tokens