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 nolte/claude-home-assistant --skill ha-esphome-display-authorgit clone --depth 1 https://github.com/nolte/claude-home-assistantWrote 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/nolte/claude-home-assistant/ha-esphome-display-author)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-esphome-display-author"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-esphome-display-author/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/nolte/claude-home-assistant/ha-esphome-display-author"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-esphome-display-author.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00265 | $0.02938 |
| Opus 5 | $0.00133 | $0.01469 |
| Sonnet 5 | $0.00053 | $0.00588 |
| Haiku 4.5 | $0.00026 | $0.00294 |
Grade A, and why
ha-esphome-display-author 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA ESPHome Display Author
Spec: spec/claude/ha-esphome-display-author/en.md (EN canonical) / spec/claude/ha-esphome-display-author/de.md (DE translation). Grounding specs: spec/ha/esp32-s3-box-display/en.md (rendering mechanics, canonical for the 320×240 panel), spec/ha/esp32-s3-box-display-design/en.md (the design system layered on those mechanics — palette, type scale, icon scale, structure), and spec/ha/esp32-s3-box/en.md §Display binding (the hardware side, referenced not repeated).
Authors what is on the screen and where — the pages, the redraw discipline, the geometry, and the design system applied to them — for one display of one device per invocation.
Why this is a skill, not an agent
- Mid-flow approval is the contract (decisive): the rendering-path choice is expensive to reverse (page lambdas and widget trees share no code, so switching later is a rewrite of the whole UI), and the state-to-page mapping is a design conversation, not a derivation.
- Iterated visual work in the current context: layouts are adjusted in rounds — a zone moved, a font size dropped, a string truncated — which is main-thread territory.
- Counter-dimension considered: the asset and memory budgeting is mechanical enough to isolate (agent bias), but it feeds directly back into the layout decisions being discussed; skill wins.
When this skill activates
The user wants content on an ESPHome device's panel — "was soll auf dem Display der Box stehen", "add a page for the timer", "design the idle screen" — for a device whose display is already bound.
When NOT to activate
- the panel's hardware binding (SPI pins,
model:preset,invert_colors, backlight light) →ha-esphome-config-augment, taking the values fromspec/ha/esp32-s3-box/en.md - where the displayed values come from →
ha-esphome-binding-add - the voice-assistant lifecycle that drives the reference screens →
ha-esphome-voice-satellite-add - a Divoom Pixoo 64 →
ha-pixoo-solution(a different device family with its own specs) - a panel geometry other than 320×240 → the grounding specs' constants are specific to this panel: the zone grid to 320×240, and the design spec's legibility table and icon sizes to its 2.4-inch, 166.7 ppi geometry. State that limit rather than extrapolating
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 · 109 lines · 265 tokens per session scan A 6e5a5120175f
ha-esphome-display-author is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 265 tokens to every session and 2,938 once invoked, about $0.0013 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
embedded-iot
Embedded systems firmware, microcontrollers (ESP32, STM32, Arduino, Raspberry Pi), RTOS (FreeRTOS, Zephyr), IoT protocols (MQTT, CoAP, BLE), bare-metal C/C++, and hardware peripheral interfaces (I2C, SPI, UART, GPIO). Use when developing firmware, working with microcontrollers, or building IoT devices.
c-display
Control display brightness and safely move files to trash instead of permanently deleting with rm.
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.