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.
npx agentmods add skills/home-assistant/core/ha-pr-comment-auditnpx skills add home-assistant/core --skill ha-pr-comment-auditgit clone --depth 1 https://github.com/home-assistant/coreWhat 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 | $0.00053 | $0.00205 |
| Opus 5 | $0.00026 | $0.00102 |
| Sonnet 5 | $0.00011 | $0.00041 |
| Haiku 4.5 | $0.00005 | $0.00020 |
Grade A, and why
ha-pr-comment-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 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.
What it actually says
Check Home Assistant PR Review Comments
Instructions:
- Resolve the PR context first. If a PR number is not given, use 'gh pr view' to identify the current branch's PR.
- Fetch the review comment threads for the PR (e.g. 'gh api' for review threads/comments).
- Flag comments that have not been addressed. If the author has replied but has not implemented the suggestion, still flag it and summarize the reply.
- Flag comments for which the author has asked for clarification.
- Generate a summary of the flagged comments, including a link for each comment. Don't include comments that have been addressed.
IMPORTANT:
- Only provide feedback in the CONSOLE. DO NOT ACT ON GITHUB.
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.
- today First seen · 18 lines · 53 tokens per session scan A 14800affcd30
ha-pr-comment-audit is a skill published in the GitHub repository home-assistant/core (90,198 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 205 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 2026-08-31.
Other skills, from other repositories
iot-developer
Expert in IoT development, microcontrollers, sensors, and MQTT protocols.
edge-iot
Edge computing, IoT protocols, and embedded systems integration.
acme-cse
Answer questions about the ACME oneM2M CSE open source project — installation, configuration, runtime options, protocol bindings, plugins, scripting, and development. Use this skill whenever the user asks anything about ACME CSE, oneM2M, acmecse, acme.ini, CSE setup, or running/configuring the ACME middleware, even if…
aether-iot-query
Use this skill when the user asks about a live AetherEdge runtime: channels, points, real-time values, history, alarms, rules, models, instances, routing, SHM health, service health, or system status. Use aether CLI commands to answer — do NOT inspect source code, local database files, or config YAMLs to answer…
aether-iot
Build, integrate, diagnose, or generate applications for the AetherEdge AI-native edge kernel. Use for AetherEdge onboarding, SDK compositions, device and topology clients, read-only operations UIs, MCP integration, Domain Packs, or governed IoT commands where live-state authority and physical-device safety must be…
devices-mcp-home
Live inventory of the user's smart home on this devices-mcp installation — cameras, Hue lights, Tapo P115 plugs, Netatmo weather, Ring, Nest Protect, Shelly sensors, and robots. Use when the user asks what devices they have, what's online, or wants a status summary before controlling hardware.