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-safety-audit)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/ha-safety-audit"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/ha-safety-audit.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 | $0.00053 | $0.00492 |
| Opus 5 | $0.00026 | $0.00246 |
| Sonnet 5 | $0.00011 | $0.00098 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
ha-safety-audit 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.
What it actually says
HA Safety Audit
Purpose
The plugin's safety gate only runs when automations are built through ha-build-automation. Automations and scripts added directly via the HA UI bypass it. This skill re-audits every live automation and script against the current safety policy and surfaces violations so the operator can review them.
Violations listed in .claude-code-hermit/compiled/acknowledged-violations.md (under automation_ids or script_ids) are suppressed from the actionable findings and reported separately as acknowledged.
Steps
- Run
${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha audit-automations. - Run
${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha audit-scripts. - Each command writes JSON + markdown artifacts under
.claude-code-hermit/raw/audit-ha-safety-*and.claude-code-hermit/raw/audit-ha-script-safety-*and prints a stdout findings block. - Concatenate the two stdout blocks with a blank separator line and pass the result through unchanged — reflect --scheduled-checks consumes it as the scheduled check output.
Output contract
Each CLI command prints a block in this shape:
ha-safety-audit findings — YYYY-MM-DD
Policy violations: N
- <alias> (`<id>`): <reasons>
No action needed: M automations passed
Acknowledged (suppressed): K
Scripts use ha-script-safety-audit findings — YYYY-MM-DD as the first line and scripts in place of automations.
If no violations: No actionable findings. (N automations scanned) or No actionable findings. (N scripts scanned).
Failure modes
- HA unreachable → CLI exits non-zero with an error message. Treat that as "skipped, cannot audit" in reflect --scheduled-checks context; do not retry automatically.
- No automations or scripts configured →
No actionable findings. (0 automations/scripts scanned)— not an error.
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 · 44 lines · 53 tokens per session scan A a4f64f2cd198
ha-safety-audit is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 492 once invoked, about $0.0003 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.