ha-pattern-analyst

ha-pattern-analyst is an agent for Claude Code from gtapps/claude-code-hermit. It costs 31 tokens per session (866 once invoked), scanned A, original, MIT.

A read-only Home Assistant analysis agent that examines device history and entity data to find usage patterns, unusual energy use, inactive devices, and possible automations.

In plain words
What is it for?
Use it to inspect seven-day activity, unavailable devices, silent sensors, dead automations, and changes from earlier analyses.
Why use it?
It turns raw smart-home records into clues about problems and useful routines without changing the system.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the claude-code-homeassistant-hermit plugin — 18 skills, 3 agents shipped together

Good fit Use it to inspect seven-day activity, unavailable devices, silent sensors, dead automations, and changes from earlier analyses.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gtapps/claude-code-hermit/ha-pattern-analyst
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/gtapps/claude-code-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-pattern-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/gtapps/claude-code-hermit/ha-pattern-analyst.svg)](https://agentmods.dev/agents/gtapps/claude-code-hermit/ha-pattern-analyst)
Your own site
<a href="https://agentmods.dev/agents/gtapps/claude-code-hermit/ha-pattern-analyst"><img src="https://agentmods.dev/badge/agents/gtapps/claude-code-hermit/ha-pattern-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 866 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 $0.00031 $0.00866
Opus 5 $0.00015 $0.00433
Sonnet 5 $0.00006 $0.00173
Haiku 4.5 $0.00003 $0.00087

Measured today against content hash 86e43c991203, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ha-pattern-analyst 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 today.

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/agents/ha-pattern-analyst.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a pattern analyst for Home Assistant data.

Your Job

Analyze artifacts to find:

  • Usage patterns (time-of-day, day-of-week for device activity)
  • Unused or inactive devices
  • Energy consumption anomalies
  • Entities stuck in unavailable/unknown
  • Correlated state changes that suggest automation opportunities
  • Drift from known patterns (compared to previous analysis)

Data Sources

  • .claude-code-hermit/raw/snapshot-ha-normalized-latest.json — current entity/service index, including the silence_summary block (keys: dead_automations, silent_event_sensors, inactive_candidates_by_domain, long_unavailable, suppressed_entity_domains, thresholds)
  • .claude-code-hermit/raw/snapshot-ha-history-7d-latest.json — 7-day history aggregates (keys: entity_aggregates, time_patterns, event_total, requested_entities, returned_entities, missing_entities, window_start, window_end)
  • .claude-code-hermit/raw/snapshot-ha-pattern-analysis-latest.json — previous analysis
  • .claude-code-hermit/raw/snapshot-ha-pattern-analysis-*.json — historical analysis files
  • .claude-code-hermit/raw/audit-ha-context-refresh-latest.md — last context refresh stats

Memory Cross-Reference

Auto memory is loaded in your context. Match candidates against existing memory entries using title, description, and body fields (Why:, How to apply:). Only a memory that records an operator decision can suppress: its type is feedback or project, read from the entry's frontmatter type (top level in some files, nested under metadata: in others, so check both) or, when the frontmatter is not visible, from its feedback_/project_ filename prefix. Type reference (an observed fact), type user (who the operator is), and an absent type inform the finding but never suppress it. For any candidate pattern, anomaly, opportunity, or reliability issue: if such a memory already records the operator's decision, preference, or pattern this candidate would surface, do not emit it under the regular arrays. Append it to suppressed[] with code: "covered-by-memory", a one-sentence reason, the verbatim quoted_line from memory, and memory_ref (source filename) so the operator can locate and revise stale entries.

Read the full file on GitHub · 59 lines

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. today Changed 86e43c991203
  2. 3d ago First seen · 59 lines · 31 tokens per session scan A 6e8e4aea443c

Subscribe to this mod's changes

ha-pattern-analyst is an agent published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 866 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.

Related

Other agents, from other repositories

c-embedded-architect

C embedded systems (bare-metal / RTOS) architecture specialist. Validates HAL/driver/app layering, ISR discipline, dynamic allocation rules, volatile usage, and global state hygiene. Dispatch when touching HAL, drivers, application code, or RTOS wrappers.

onlygian/G-Forge · 57 tokens

qec-hardware-engineer

QECTOR hardware/quantum-architecture engineer. Use for Stim circuit imports, Detector Error Models, qLDPC and hyperedge decode, and honest hardware/GPU reporting.

GuillaumeLessard/qector-claude-plugin · 42 tokens

part-sourcer

Use this agent to find the best JLCPCB-stocked LCSC part matching a generic component spec. Given something like "3.3V LDO regulator, SOT-23-5, 500mA out, basic-tier preferred", returns one recommended pick plus 2 alternates with cost-impact annotations. Hard-prefers basic-library parts to avoid the JLCPCB…

BeckhamLabsLLC/kicad-jlcpcb · 198 tokens

jensen-huang

Jensen Huang — Hardware & AI Infrastructure. Spawnable director agent for AI infrastructure planning, GPU and data center strategy, performance and cost optimization, and build-vs-buy decisions on compute. Use when compute, energy, or infrastructure is the bottleneck.

markusbegerow/board-of-directors · 56 tokens

network-architect

Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.

affaan-m/ECC · 31 tokens

plan-creation-eng-lead

Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.

QBall-Inc/the-bulwark · 48 tokens