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 skills add tonylofgren/aurora-smart-home --skill esphomegit clone --depth 1 https://github.com/tonylofgren/aurora-smart-homeWrote 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/tonylofgren/aurora-smart-home/esphome)<a href="https://agentmods.dev/skills/tonylofgren/aurora-smart-home/esphome"><img src="https://agentmods.dev/badge/skills/tonylofgren/aurora-smart-home/esphome/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tonylofgren/aurora-smart-home/esphome"><img src="https://agentmods.dev/badge/skills/tonylofgren/aurora-smart-home/esphome.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 87 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 96 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 130 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 315 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 388 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 517 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00192 | $0.06597 |
| Opus 5 | $0.00096 | $0.03299 |
| Sonnet 5 | $0.00038 | $0.01319 |
| Haiku 4.5 | $0.00019 | $0.00660 |
Grade A, and why
ESPHome 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESPHome Devices
Reference skill for ESPHome device configuration and firmware.
Overview
Core principle: Never generate ESPHome configuration without knowing the exact hardware. Board selection determines GPIO mapping, flash size, available features, and component compatibility.
Context: This skill requires hardware confirmation before any YAML generation. Different ESP chips have vastly different capabilities - ESP32-S3 supports USB and cameras, ESP32-C6 supports Thread/Matter/WiFi 6, ESP32-H2 is BLE+Thread only (no WiFi), ESP32-P4 is high-performance with MIPI DSI displays, and ESP8266 has limited GPIO and memory. ESPHome also supports nRF52 (Zephyr), RP2040, and LibreTiny (BK72xx/RTL87xx) platforms.
The Iron Law
CONFIRM BOARD BEFORE GENERATING ANY CONFIGURATION
ESP32 has 12+ variants with different GPIO mappings, strapping pins, and capabilities. Assuming esp32dev when the user has an S3, C3, or C6 produces configs that silently fail. Always get explicit board confirmation first.
The Process
User request
│
▼
Ask: What board?
│
▼
Board confirmed? ──no──▶ Ask again
│ yes
▼
Battery/actuator/outdoor/>5V? ──yes──▶ Vera: Hardware Safety Review
│ no (or cleared by Vera) │ blocks if critical risk found
▼ ▼
Ask: Output method? ◀── safety cleared
│
▼
deep_sleep / battery / solar / power bank? ──yes──▶ Flag Watt for power budget
│ no (or after Watt)
▼
Read relevant references
│
▼
Generate YAML config
│
▼
Generate wiring diagram (every GPIO — no exceptions)
│
▼
Calibration procedure needed? ──yes──▶ Generate procedure with actual entity IDs
│ no
▼
Generate troubleshooting section (3 most likely failure points)
│
▼
Run pre-completion checklist
│
▼
Deliver config
Common Pitfalls
Watch out for these assumptions:
| Thought | Reality |
|---|---|
| "They probably mean ESP32" | ASK. ESP32 has 12+ variants with different pinouts |
| "I'll use esp32dev as default" | WRONG. Could be S3, C3, C6, or commercial device |
| "The GPIO numbers look standard" | Strapping pins vary by chip. Confirm board first |
| "It's just a simple sensor" | Simple configs still need correct board ID |
| "I can infer from the project" | Never infer. Always confirm |
| "secrets.yaml is just a file" | NEVER touch secrets.yaml. Use !secret references only |
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/templates/air-quality-monitor.yaml 6.8 KB
- assets/templates/alarm-panel.yaml 2.8 KB
- assets/templates/base-esp32.yaml 1.8 KB
- assets/templates/base-esp8266.yaml 1.6 KB
- assets/templates/battery-sensor.yaml 3.1 KB
- assets/templates/ble-presence.yaml 2.8 KB
- assets/templates/ble-proxy.yaml 5.1 KB
- assets/templates/display-oled.yaml 3.7 KB
- assets/templates/eink-dashboard.yaml 8.4 KB
- assets/templates/energy-monitor-emontx.yaml 9.0 KB
- assets/templates/espnow-hub.yaml 6.4 KB
- assets/templates/espnow-node.yaml 5.1 KB
- assets/templates/garage-door.yaml 3.7 KB
- assets/templates/ir-remote-hub.yaml 3.3 KB
- assets/templates/irrigation-controller.yaml 3.5 KB
- assets/templates/led-matrix-clock.yaml 4.0 KB
- assets/templates/led-strip-effects.yaml 5.2 KB
- assets/templates/lora-sensor-node.yaml 8.4 KB
- assets/templates/matter-light.yaml 4.9 KB
- assets/templates/media-player.yaml 2.6 KB
- assets/templates/mmwave-multi-target.yaml 6.2 KB
- assets/templates/motorized-blinds.yaml 9.8 KB
- assets/templates/mqtt-gateway.yaml 2.1 KB
- assets/templates/README.md 8.2 KB
- assets/templates/sensor-multi.yaml 1.9 KB
- assets/templates/shelly-1pm.yaml 2.2 KB
- assets/templates/smart-doorbell.yaml 6.7 KB
- assets/templates/sonoff-basic.yaml 1.6 KB
- assets/templates/tank-level-monitor.yaml 7.4 KB
- assets/templates/thermostat.yaml 3.8 KB
- assets/templates/touch-panel.yaml 4.4 KB
- assets/templates/voice-assistant.yaml 7.6 KB
- assets/templates/washing-machine-monitor.yaml 6.6 KB
- assets/templates/water-leak-sensor.yaml 5.9 KB
- assets/templates/web-dashboard.yaml 2.5 KB
- assets/templates/weight-scale.yaml 6.6 KB
- CHEATSHEET.md 6.8 KB
- components/panasonic_ac/__init__.py 0 B runs code
- components/panasonic_ac/climate.py 5.1 KB runs code
- components/panasonic_ac/esppac_cnt.cpp 16 KB
- components/panasonic_ac/esppac_cnt.h 1.8 KB
- components/panasonic_ac/esppac_commands_cnt.h 1013 B
- components/panasonic_ac/esppac_commands_wlan.h 2.4 KB
- components/panasonic_ac/esppac_wlan.cpp 27 KB
- components/panasonic_ac/esppac_wlan.h 2.9 KB
- components/panasonic_ac/esppac.cpp 10 KB
- components/panasonic_ac/esppac.h 5.4 KB
- components/panasonic_ac/LICENSE 1.0 KB
- components/panasonic_ac/NOTICE.md 4.1 KB
- components/panasonic_ac/panasonic_ac_select.h 362 B
- components/panasonic_ac/panasonic_ac_switch.h 353 B
- images/supercharge2.png 1416 KB
- INSTALLATION.md 3.0 KB
- LICENSE 1.0 KB
- m5stack-atom-echo-voice-assist.yaml 4.2 KB
- m5stack-atom-echo-voice.yaml 3.0 KB
- PROMPT-IDEAS.md 46 KB
- README.md 16 KB
- references/alarm-security.md 17 KB
- references/arduino-conversion.md 19 KB
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.
- 12d ago First seen · 538 lines · 192 tokens per session scan A d8e14093811b
ESPHome is a skill published in the GitHub repository tonylofgren/aurora-smart-home (104 stars, last pushed 7d ago), licensed MIT. It adds 192 tokens to every session and 6,597 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
bat-story-eval
Compare MCP tool behavior between target and baseline versions using pre-built and custom stories with diff-based triage.
contrib-pr-review
Review a contribution PR for safety, quality, and readiness. Checks for security concerns, test coverage, size appropriateness, and intent alignment. Use when reviewing external contributions.
bat-adhoc
Run bot acceptance tests to validate MCP tools work correctly from a real AI agent's perspective. Use when testing PRs, detecting regressions, or verifying tool changes end-to-end with Claude/Gemini CLIs.
issue-to-pr-resolver
Implement a GitHub issue end-to-end — create a worktree branch, implement the feature with tests, create a draft PR, then iteratively resolve all CI failures and review comments until the PR is clean. Use when you need to fully implement a GitHub issue from start to merge-ready. Triggers on "implement issue", "resolve…
my-pr-checker
Manage your own GitHub pull requests — check CI status, inline review comments, PR-level comments, resolve review threads, fix issues, and iterate until all checks pass and threads are resolved. Use for managing your own PRs (not external contributions). Triggers on "check my PR", "check PR", "/my-pr-checker ".
contributors-update
Find merged PR authors missing from README and update the contributors list after approval.