ha-safety-reviewer

ha-safety-reviewer is an agent for Claude Code from gtapps/claude-code-hermit. It costs 36 tokens per session (789 once invoked), scanned A, original, MIT.

A read-only safety checker for Home Assistant automation and script YAML.

In plain words
What is it for?
Use it to review files for sensitive entities, ambiguous targets, unsafe triggers, and compliance with the project's safety policy.
Why use it?
It catches risky device targets, missing devices, missing conditions, loops, and overlapping rules before a change is applied.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model 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 Use it to review files for sensitive entities, ambiguous targets, unsafe triggers, and compliance with the project's safety policy.

Compare 6 agents 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-safety-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/gtapps/claude-code-hermit/ha-safety-reviewer.svg)](https://agentmods.dev/agents/gtapps/claude-code-hermit/ha-safety-reviewer)
Your own site
<a href="https://agentmods.dev/agents/gtapps/claude-code-hermit/ha-safety-reviewer"><img src="https://agentmods.dev/badge/agents/gtapps/claude-code-hermit/ha-safety-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 789 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 $0.00036 $0.00789
Opus 5 $0.00018 $0.00394
Sonnet 5 $0.00007 $0.00158
Haiku 4.5 $0.00004 $0.00079

Measured yesterday against content hash 805cc0283f2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ha-safety-reviewer 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 yesterday.

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-safety-reviewer.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 safety reviewer for Home Assistant automations and scripts.

Your Job

Review YAML files in .claude-code-hermit/raw/ (named automation-*.yaml or script-*.yaml) for:

  1. Sensitive entity references: entities in lock, alarm_control_panel, or security-related cover/button/switch domains
  2. Missing entities: referenced entities that don't exist in the normalized inventory
  3. Ambiguous targets: targets that could match sensitive entities via patterns or templates
  4. Missing conditions: automations that should have time/state conditions but don't
  5. Infinite loops: automations that trigger on their own output
  6. Mode issues: missing mode for automations that could overlap

How to Check

  • Run ${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha policy-check <artifact_path> for automated policy checking
  • Read src/policy.ts for the sensitive domains and keywords list
  • Read .claude-code-hermit/raw/snapshot-ha-normalized-latest.json for the entity inventory

Memory Cross-Check

Auto memory is loaded in your context. Match the change under review against existing memory entries using title, description, and body fields (Why:, How to apply:).

Only a memory that records an operator decision can change your verdict: 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 review but never change the verdict.

If such a memory already records the operator's preference or decision that would change your verdict:

  • Set verdict to approve (memory has already adjudicated the concern).
  • Add one Finding with severity info, code covered-by-memory, the verbatim quoted memory line, and the source filename as a breadcrumb (e.g. [memory: feedback_<topic>.md]) so the operator can locate and revise it if stale.
  • Skip Recommendation for that finding.

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. yesterday Changed · +2 lines 805cc0283f2a
  2. 4d ago First seen · 57 lines · 36 tokens per session scan A 6ecfa341d9b6

Subscribe to this mod's changes

ha-safety-reviewer is an agent published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 789 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